Repository Analysis

yologdev/yoyo-evolve

A coding agent that evolves its own source, in public — 200 lines of Rust on day one, every commit since agent-written and tests-gated.

9.4 Low AI signal View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of yologdev/yoyo-evolve, a Rust project with 1,868 GitHub stars. SynthScan v2.0 examined 202,620 lines of code across 212 source files, recording 1080 pattern matches distributed across 15 syntactic categories. The overall adjusted score of 9.4 places this repository in the Low AI signal band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

9.4
Adjusted Score
9.4
Raw Score
100%
Time Factor
2026-08-29
Last Push
1.9K
Stars
Rust
Language
202.6K
Lines of Code
212
Files
1.1K
Pattern Hits
2026-08-29
Scan Date
0.00
HC Hit Rate

What These Metrics Mean

Adjusted Score
Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score
The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor
The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits
Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate
High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files
Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 1MEDIUM 415LOW 664

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 1080 distinct pattern matches across 15 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Decorative Section Separators341 hits · 1023 pts
SeverityFileLineSnippetContext
MEDIUMtests/harness_logic.sh23# ── session budget helper ────────────────────────────────────────────────COMMENT
MEDIUMtests/harness_logic.sh40# ── gate thresholds vs the timeouts they must cover ──────────────────────COMMENT
MEDIUMtests/harness_logic.sh56# ── coupled numbers: prompts must agree with the code ────────────────────COMMENT
MEDIUMtests/harness_logic.sh68# ── ordering invariant: NO function called above its definition ──────────COMMENT
MEDIUMtests/harness_logic.sh97# ── failed-test name extraction: exercise evolve.sh's OWN regex ──────────COMMENT
MEDIUMtests/harness_logic.sh106# ── scope-review checklist: prompt items == parser items (#712) ──────────COMMENT
MEDIUMtests/harness_logic.sh224# ── cross-file coupling: evolve.sh gates vs evolve.yml budgets ───────────COMMENT
MEDIUMtests/harness_logic.sh242# ── GASP: exactly one writer to the state store (#683) ───────────────────COMMENT
MEDIUMtests/harness_logic.sh297# ── eval-fix loop: the no-progress detector ──────────────────────────────COMMENT
MEDIUMtests/harness_logic.sh314# ── the no-progress COUNTER, not just its constants ──────────────────────COMMENT
MEDIUMtests/integration.rs36// ── --help ──────────────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs78// ── --version ───────────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs117// ── Empty stdin (piped mode) ────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs212// ── Unknown flags ───────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs234// ── --no-color suppresses ANSI codes ────────────────────────────────COMMENT
MEDIUMtests/integration.rs271// ── Missing API key ────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs337// ── Flags requiring values show clear errors ────────────────────────COMMENT
MEDIUMtests/integration.rs380// ── /help output lists all documented commands ──────────────────────COMMENT
MEDIUMtests/integration.rs453// ── --no-color output contains no ANSI escape sequences ─────────────COMMENT
MEDIUMtests/integration.rs498// ── Multiple unknown flags each produce warnings ────────────────────COMMENT
MEDIUMtests/integration.rs538// ── --system-file with nonexistent file shows useful error ──────────COMMENT
MEDIUMtests/integration.rs586// ── Piped input with bad API key (needs network) ────────────────────COMMENT
MEDIUMtests/integration.rs588// ── --thinking without a value ───────────────────────────────────────COMMENT
MEDIUMtests/integration.rs611// ── --verbose flag accepted ─────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs649// ── --allow and --deny flags accepted ───────────────────────────────COMMENT
MEDIUMtests/integration.rs719// ── --model without value (specific exit code + error format) ───────COMMENT
MEDIUMtests/integration.rs746// ── Unknown slash-command-like arguments don't crash ────────────────COMMENT
MEDIUMtests/integration.rs770// ── Piped input with bad API key (needs network) ────────────────────COMMENT
MEDIUMtests/integration.rs817// ── Error message quality ───────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs921// ── Flag combinations ───────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs1002// ── Exit codes ──────────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs1059// ── Output format ───────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs1159// ── Edge cases ──────────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs1336// ── UX timing tests ─────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs1488// ── Dogfood UX verification tests (Issue #69) ──────────────────────COMMENT
MEDIUMtests/integration.rs1488// ── Dogfood UX verification tests (Issue #69) ──────────────────────COMMENT
MEDIUMtests/integration.rs1696// ── --allow-dir and --deny-dir flags ────────────────────────────────COMMENT
MEDIUMtests/integration.rs1809// ── /plan command ────────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs1825// ── --image flag ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs1915// ── Benchmark-relevant properties ───────────────────────────────────COMMENT
MEDIUMtests/integration.rs1989// ── Setup wizard wiring (Issue #157) ────────────────────────────────COMMENT
MEDIUMtests/integration.rs1989// ── Setup wizard wiring (Issue #157) ────────────────────────────────COMMENT
MEDIUMtests/integration.rs2125// ── --no-bell ───────────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs2146// ── /map command ─────────────────────────────────────────────────────COMMENT
MEDIUMtests/integration.rs2164// ── MCP collision guard (Day 39) ─────────────────────────────────────COMMENT
MEDIUMtests/integration.rs2193// ── Skill loader contract regression guard ────────────────────────────COMMENT
MEDIUMscripts/measure_abstentions.py774# ---------------------------------------------------------------------------COMMENT
MEDIUMscripts/measure_abstentions.py776# ---------------------------------------------------------------------------COMMENT
MEDIUMscripts/measure_abstentions.py167# ── Markers ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMscripts/measure_abstentions.py1088# ── I/O (kept at the call sites; everything above is pure) ────────────────────COMMENT
MEDIUMscripts/measure_abstentions.py1298# ── Self-tests ────────────────────────────────────────────────────────────────COMMENT
MEDIUMscripts/measure_abstentions.py1886 # ------------------------------------------------------------------COMMENT
MEDIUMscripts/measure_abstentions.py1889 # ------------------------------------------------------------------COMMENT
MEDIUMscripts/check_assertion_weakening.py59# --------------------------------------------------------------------------------------COMMENT
MEDIUMscripts/check_assertion_weakening.py61# --------------------------------------------------------------------------------------COMMENT
MEDIUMscripts/check_assertion_weakening.py91# --------------------------------------------------------------------------------------COMMENT
MEDIUMscripts/check_assertion_weakening.py93# --------------------------------------------------------------------------------------COMMENT
MEDIUMscripts/check_assertion_weakening.py208# --------------------------------------------------------------------------------------COMMENT
MEDIUMscripts/check_assertion_weakening.py210# --------------------------------------------------------------------------------------COMMENT
MEDIUMscripts/check_assertion_weakening.py331# --------------------------------------------------------------------------------------COMMENT
281 more matches not shown…
Over-Commented Block560 hits · 530 pts
SeverityFileLineSnippetContext
LOWtests/orphan_modules.rs1//! Orphan-module gate: every `*.rs` file under `src/` must be named by someCOMMENT
LOWtests/orphan_modules.rs21//! as "checked; clean".COMMENT
LOWtests/orphan_modules.rs41COMMENT
LOWtests/doc_version_claims.rs1//! Freshness gate for prose claims about what an **external dependency**COMMENT
LOWtests/doc_version_claims.rs21//! This lives in `tests/` rather than inside the modules it scans on purpose:COMMENT
LOWtests/doc_version_claims.rs81COMMENT
LOWtests/doc_version_claims.rs221 // Line numbers are 1-based and several markers in one file are all seen —COMMENT
LOWtests/feature_gated_tests.rs1//! Feature-gated test-visibility gate: every `tests/*.rs` file whose firstCOMMENT
LOWtests/feature_gated_tests.rs21//! `tests/blind_round_grades.rs`, `tests/orphan_modules.rs`,COMMENT
LOWtests/feature_gated_tests.rs41//! that I knew a file was invisible to the harness — it is not evidence thatCOMMENT
LOWtests/system_prompt_chokepoint.rs1//! Choke-point gate: every production `with_system_prompt` call must routeCOMMENT
LOWtests/system_prompt_chokepoint.rs21//! is the safe one: it fails loudly rather than passing quietly.COMMENT
LOWtests/blind_round_grades.rs1//! Structural gate: a blind round that predicted must also grade.COMMENT
LOWtests/blind_round_grades.rs21//!COMMENT
LOWtests/blind_round_grades.rs41//! partially graded round did teach something. Same message shape (round,COMMENT
LOWtests/blind_round_grades.rs61//!COMMENT
LOWtests/blind_round_grades.rs81/// without its grade and that I knew. The ratchet in branch 3 is what keeps itCOMMENT
LOWtests/cargo_spawning_tests.rs1//! Cargo-spawning-test gate: a `#[test]` under `src/` that reaches a `cargo`COMMENT
LOWtests/cargo_spawning_tests.rs21//! gives an N/N counter that feels like closure while the property staysCOMMENT
LOWtests/cargo_spawning_tests.rs41//! `Command::new("cargo")`) finds **zero** violations today and would beCOMMENT
LOWtests/cargo_spawning_tests.rs61//! 1. **One hop only.** A test reaching a spawner through an intermediateCOMMENT
LOWtests/cargo_spawning_tests.rs81//! and the scanner is pinned by its own table test.COMMENT
LOWtests/harness_logic.sh1#!/usr/bin/env bashCOMMENT
LOWtests/harness_logic.sh241COMMENT
LOWtests/module_size.rs1//! Structural smoke gate: a deterministic module line-count cap over `src/`.COMMENT
LOWtests/module_size.rs21//! blowing 50+ lines past the cap in one task *is* the design event. ThatCOMMENT
LOWtests/module_size.rs41//! damage is to branch 3: a stale-high entry does not break the ratchet, itCOMMENT
LOWtests/module_size.rs61COMMENT
LOWtests/module_size.rs81/// reverting the task teaches nothing the warning cannot.COMMENT
LOWtests/module_size.rs101/// with **no reader**. It goes to the stderr of a *passing* test, and the onlyCOMMENT
LOWtests/module_size.rs121///COMMENT
LOWtests/module_size.rs141 // Day 164 (#728): +98 lines — `/skill install`'s destination becomes a thirdCOMMENT
LOWtests/module_size.rs161 // conflicted files honestly instead of "all strategies failed".COMMENT
LOWtests/module_size.rs181 // (map, annotation, helper, and the test pinning them); see #724.COMMENT
LOWtests/module_size.rs201 // guaranteed never-forecast status and leading the list that steers theCOMMENT
LOWtests/module_size.rs221 // pinning that a text-less newest turn yields None, not an older turn's text.COMMENT
LOWtests/module_size.rs241 // `print_context_usage` / `contextual_hint` with their doc comments, oneCOMMENT
LOWtests/module_size.rs261 // mechanical, plus the test that pins the emitted bytes.COMMENT
LOWtests/module_size.rs281 // matcher this deliberately avoids.COMMENT
LOWtests/module_size.rs301 // guard (two constructors) + three Arc-path enforcement tests. The testsCOMMENT
LOWtests/module_size.rs321 // build_watch_fix_prompt, with its own test; see #724.COMMENT
LOWtests/module_size.rs361 ceiling: usize,COMMENT
LOWtests/module_size.rs501/// I/O stays at the single call site.COMMENT
LOWtests/global_state_races.rs1//! Shared-global test-race gate: a `#[test]` in `src/` that writes aCOMMENT
LOWtests/global_state_races.rs21//! buys the enumeration.COMMENT
LOWtests/global_state_races.rs41//! off after eight days of nobody reading a passing test's warning.COMMENT
LOWtests/global_state_races.rs61//! none in `src/` today, and the scanner is pinned by its own table test.COMMENT
LOWtests/global_state_races.rs181 // test IS the global setter (`enable_quiet` is `QUIET.set(true)`,COMMENT
LOWtests/gasp_session_end_guard.rs1//! Source-level ordering guard for `gasp::session_end`'s session-node close (#849).COMMENT
LOWtests/gasp_session_end_guard.rs21//! **Why this file is not feature-gated, deliberately.** `src/gasp.rs` sitsCOMMENT
LOWtests/gasp_cli_run_ordering.rs1//! #831 — a four-call `yoyo gasp` session must not interrupt its own run.COMMENT
LOWtests/gasp_cli_run_ordering.rs21//!COMMENT
LOWtests/gasp_cli_run_ordering.rs41//! The whole file is `#![cfg(feature = "gasp")]`, so a **plain** `cargo test`COMMENT
LOWtests/gasp_cli_run_ordering.rs221COMMENT
LOWtests/integration.rs2161 // is in unit tests (map_in_help_text).COMMENT
LOWtests/integration.rs2241 "skill-evolve meta-skill must be present"COMMENT
LOW.cargo/mutants.toml1# cargo-mutants configuration for yoyoCOMMENT
LOW.cargo/mutants.toml21# failed to start. The live key is `exclude_re`: a list of regexps matchedCOMMENT
LOW.cargo/mutants.toml41# CLAUDE.md records mutation readings for these five files:COMMENT
LOWscripts/measure_abstentions.py181# a silently-absorbed unknown inside my own meter is the defect this tool exists for)COMMENT
500 more matches not shown…
AI Slop Vocabulary57 hits · 177 pts
SeverityFileLineSnippetContext
MEDIUMtests/harness_logic.sh2# Structural tests for the harness and its cross-file contracts — the pureCOMMENT
MEDIUMtests/harness_logic.sh6# The harness grew to ~3k lines of interlocking gates whose only automatedCOMMENT
MEDIUMtests/harness_logic.sh354 # Non-empty diff — green work exists. Must NOT convert the harness'sCOMMENT
MEDIUMscripts/measure_abstentions.py342# text*, not harness stdout, so a log containing nothing but an echoed prompt wouldCOMMENT
MEDIUMscripts/measure_abstentions.py348# harness output.COMMENT
MEDIUMscripts/measure_abstentions.py357# SESSION_FOOTER are deliberately absent: they are bookends the harness prints whetherCOMMENT
MEDIUMscripts/measure_abstentions.py780# the `audit-log` branch does not contain the harness's stdout — it contains agentCOMMENT
MEDIUMscripts/measure_abstentions.py781# transcripts and files the harness writes. So measuring a session *directory* forCOMMENT
MEDIUMscripts/measure_abstentions.py788# Why artifacts rather than more greps: these files are written by the harness into theCOMMENT
MEDIUMscripts/measure_abstentions.py209# no-harness-output one rather than replacing it. Buckets are referred to BY NAME andCOMMENT
MEDIUMscripts/measure_abstentions.py222# Why that inverts the metric: "the harness printed something" and "the harness got farCOMMENT
MEDIUMscripts/measure_abstentions.py248# Anchored shapes. Each is the harness's WHOLE emitted line from its first word toCOMMENT
MEDIUMscripts/measure_abstentions.py312 # the PROVIDER's string, not the harness's, and the phrase list mirrorsCOMMENT
MEDIUMscripts/measure_abstentions.py320# Tells that a line is my own writing (or a tool quoting a file) rather than harnessCOMMENT
MEDIUMscripts/measure_abstentions.py1011 # no unquoted harness marker was not measured at all, so it must not stand in for aCOMMENT
MEDIUMscripts/measure_abstentions.py1212 # carries harness markers" and "age comes from a day-N-<ts> filename" — used toCOMMENT
MEDIUMscripts/measure_abstentions.py1308 # 1. The four real harness lines classify correctly (verbatim from evolve.sh).COMMENT
MEDIUMscripts/measure_abstentions.py1403 # A real log carries harness stdout; without a phase marker thisCOMMENT
MEDIUMscripts/measure_abstentions.py1814 # A real log carries harness stdout; without a phase marker thisCOMMENT
MEDIUMscripts/measure_abstentions.py2005 # (g) Byte-identity for the healthy path: with harness output everywhere, `grade`COMMENT
MEDIUMscripts/measure_abstentions.py2026 # three `=== Day N (...) ===` headers each — harness output present, no phase.COMMENT
MEDIUMscripts/measure_abstentions.py2143 # carries harness markers" and "age comes from a day-N-<ts> filename" — composedCOMMENT
MEDIUMscripts/measure_abstentions.py2186 # assertion must not overwrite a stamp the harness itself wrote.COMMENT
MEDIUMscripts/test_scan_commitments.py167 # an empty result — "couldn't check" must not reach the harness asCOMMENT
MEDIUMscripts/test_scan_commitments.py384 """The exact failure mode the human named on #589: when the harnessSTRING
MEDIUMscripts/evolve.sh422# Inline cleanup is robust to that risk; PID-suffixed worktree paths boundCOMMENT
MEDIUMscripts/evolve.sh472# Keep core skills in ./skills, but allow the harness to fetch reusable externalCOMMENT
MEDIUMscripts/evolve.sh814# progress and the harness fails open on a green build+test. Each body ends byCOMMENT
MEDIUMscripts/evolve.sh1003# tagged source=discussion (#589, the harness half of #582) — promises madeCOMMENT
MEDIUMscripts/evolve.sh1734 # the harness-side backstop if it writes more files anyway.COMMENT
MEDIUMscripts/evolve.sh2593 # The harness is deliberately fail-open everywhere else inCOMMENT
MEDIUMscripts/skill_evolve.sh36# the eval fact must name THIS harness's actual oracle (no clippy, noCOMMENT
MEDIUMscripts/skill_evolve.sh316 # harness-side belt that turns them into actual constraints.COMMENT
MEDIUMscripts/format_issues.py203 # to a bare "..."). The recovery command itself lives in the harness'sCOMMENT
MEDIUMscripts/extract_trajectory.py226# Verbatim title the harness writes when Phase A2 produces no task files.COMMENT
MEDIUMscripts/extract_trajectory.py1339# lookup: the harness checkout is shallow (already documented forCOMMENT
MEDIUMscripts/extract_trajectory.py1948 # so the consumer exists and needs no harness change. ONE line, so it cannotCOMMENT
MEDIUMscripts/extract_trajectory.py3424 # The harness's real numbers, 2026-08-27T07:19Z: a full page of 20 whoseSTRING
MEDIUMscripts/extract_trajectory.py3695 # State 3: the harness path. Near-miss guard — a discriminator tested onlySTRING
MEDIUMscripts/dream.sh222# Write ONLY these two files (the harness reverts anything else — this is a hard limit):COMMENT
MEDIUMscripts/bench/humaneval_run.sh6# It COMPOSES the single-case harness `humaneval_one.sh` (do NOT reinvent theCOMMENT
MEDIUMscripts/bench/humaneval_run.sh19# over the small inline problem set the single-case harness encodes.COMMENT
MEDIUMscripts/bench/humaneval_run.sh28# from the single-case harness. Do NOT hardcode the list independently.COMMENT
MEDIUMscripts/bench/humaneval_run.sh30# NOTE: this is a Kind:evolve script — a bench harness for yoyo's own capabilityCOMMENT
MEDIUMscripts/bench/humaneval_run.sh37# anywhere. The single-case harness resolves its own REPO_ROOT/cwd, so we onlyCOMMENT
MEDIUMscripts/bench/humaneval_run.sh100# other = the harness itself errored (crash, missing key, build failure).COMMENT
MEDIUMscripts/bench/humaneval_run.sh101# We count both 1 and other as "not passed", but track harness errors distinctlyCOMMENT
MEDIUMscripts/bench/humaneval_run.sh102# so a harness bug isn't silently scored as a wrong answer.COMMENT
MEDIUMscripts/bench/humaneval_run.sh137# arithmetic if python3 is absent (matches the single-case harness's posture).COMMENT
MEDIUMscripts/bench/humaneval_run.sh149# headline so a harness bug is never silently scored as a wrong answer.COMMENT
MEDIUMsrc/main_tests.rs32 // The caller already trims, but we should be robust to \n/doctor\n etc.COMMENT
MEDIUMsrc/prompt.rs2029 /// #686: the harness greps phase logs for `refused this request`. ThisCOMMENT
MEDIUMsrc/help.rs1794 "#827: harness-facing door onto the ported GASP arms, behind the \CODE
MEDIUMsrc/commands_info.rs1298/// Uses serde_json for robust parsing.COMMENT
MEDIUMsrc/tool_wrappers.rs912/// Session-wide cap on calls to high-leverage tools (`web_search`, `sub_agent`).COMMENT
MEDIUMsrc/format/markdown.rs278 // Definitely not a fence, header, or block element — flush asCOMMENT
MEDIUMsrc/format/markdown.rs321 // Definitely not a closing fence — flush as code content immediatelyCOMMENT
Hyper-Verbose Identifiers36 hits · 42 pts
SeverityFileLineSnippetContext
LOWscripts/test_lint_evolve_heredocs.py42 def test_colon_dash_form_is_caught_too(self):CODE
LOWscripts/test_lint_evolve_heredocs.py46 def test_apostrophe_outside_an_expansion_is_fine(self):CODE
LOWscripts/test_lint_evolve_heredocs.py51 def test_label_appears_in_the_report(self):CODE
LOWscripts/test_lint_evolve_heredocs.py55 def test_nested_braces_do_not_end_the_block_early(self):CODE
LOWscripts/test_lint_evolve_heredocs.py63 def test_reported_line_number_is_the_block_start(self):CODE
LOWscripts/test_lint_evolve_heredocs.py89 def test_no_argument_still_checks_the_real_evolve_sh(self):CODE
LOWscripts/measure_abstentions.py422def classify_provider_error_line(line):CODE
LOWscripts/measure_abstentions.py449def classify_harness_output_line(line):CODE
LOWscripts/test_scan_commitments.py43 def test_skips_issues_with_no_bot_comment(self):CODE
LOWscripts/test_scan_commitments.py48 def test_skips_issues_with_no_comments(self):CODE
LOWscripts/test_scan_commitments.py53 def test_finds_last_bot_comment(self):CODE
LOWscripts/test_scan_commitments.py87 def test_truncates_long_bodies(self):CODE
LOWscripts/test_scan_commitments.py95 def test_truncates_long_git_log(self):CODE
LOWscripts/test_scan_commitments.py102 def test_extracts_first_text_block(self):CODE
LOWscripts/test_scan_commitments.py107 def test_returns_none_for_malformed_json(self):CODE
LOWscripts/test_scan_commitments.py111 def test_returns_none_for_no_text_block(self):CODE
LOWscripts/test_scan_commitments.py115 def test_returns_none_for_empty_content(self):CODE
LOWscripts/test_scan_commitments.py127 def test_empty_issues_skips_api_call(self):CODE
LOWscripts/test_scan_commitments.py133 def test_issues_without_bot_comment_skip_api(self):CODE
LOWscripts/test_scan_commitments.py140 def test_renders_outstanding_block(self):CODE
LOWscripts/test_scan_commitments.py158 def test_no_outstanding_means_no_blocks(self):CODE
LOWscripts/test_scan_commitments.py177 def test_unknown_issue_number_in_response_is_skipped(self):CODE
LOWscripts/test_scan_commitments.py69 def test_includes_up_to_two_prior_comments(self):CODE
LOWscripts/test_scan_commitments.py226 def test_discussion_source_renders_discussion_header(self):CODE
LOWscripts/test_scan_commitments.py244 def test_missing_source_defaults_to_issue(self):CODE
LOWscripts/test_scan_commitments.py261 def test_issue_and_discussion_same_number_dont_collide(self):CODE
LOWscripts/test_scan_commitments.py297 def test_unknown_source_treated_as_issue(self):CODE
LOWscripts/test_scan_commitments.py360 def test_bot_comment_present_is_triaged(self):CODE
LOWscripts/test_scan_commitments.py383 def test_bot_comment_dropped_by_unpaginated_fetch_is_false_negative(self):CODE
LOWscripts/check_assertion_weakening.py225def classify_assertion_change(CODE
LOWscripts/format_discussions.py193def _paginate_replies_from_cursor(comment_id, start_cursor):STRING
LOWscripts/lint_evolve_heredocs.py45def find_param_expansion_blocks(src):CODE
LOWscripts/extract_trajectory.py500def collect_subsystem_commits() -> str | None:CODE
LOWscripts/extract_trajectory.py528def render_subsystem_concentration(CODE
LOWscripts/extract_trajectory.py1031def collect_failed_ci_fingerprints(repo: str, now: datetime | None = None) -> CiScan:CODE
LOWscripts/extract_trajectory.py1780def collect_epistemic_blind_spots() -> tuple[list[str], list[str]]:CODE
Modern AI Meta-Vocabulary12 hits · 34 pts
SeverityFileLineSnippetContext
MEDIUMCLAUDE.md193- `tool_wrappers.rs` — Tool decorator types (GuardedTool, TruncatingTool, ConfirmTool, ArcGuardedTool, AutoCheckTool, ReCODE
MEDIUMCLAUDE.md209- `format/mod.rs` — Color, constants, utility functions, re-exports, contextual command hints (`HintContext`, `contextuaCODE
MEDIUMCLAUDE.md227- `commands_project.rs` — `/context`, `/init`, `/docs`, project-type detection, `auto_context_for_prompt` (automatic filCODE
MEDIUMCLAUDE.md265- `commands_spawn.rs` — `/spawn` subagent orchestration: SpawnTracker, worktree isolation (with a symlink pre-flight — `CODE
MEDIUMjournals/llm-wiki.md17Added MCP documentation to the README so external agents can actually discover the server, created `mcp.json` as the staCODE
MEDIUMjournals/llm-wiki.md23Extended the MCP server with three new tools: `create_page`, `update_page`, and `agent_context` — so external agents canCODE
MEDIUMscripts/test_scan_commitments.py178 # Defensive: LLM hallucinates an issue number we didn't pass in.COMMENT
MEDIUMscripts/scan_commitments.py361 # hallucinations are a signal the prompt or model is misbehaving.COMMENT
MEDIUMskills/skill-creator/SKILL.md104### 6. Generate the SKILL.md scaffoldCOMMENT
MEDIUMsrc/commands_session.rs156/// This runs BEFORE a prompt attempt (not after) to prevent overflow during agentic execution.COMMENT
MEDIUMsrc/commands_spawn.rs1093 // failure is a dim note, never a blocker (#341, orchestration scale).COMMENT
MEDIUMsrc/commands_spawn.rs3499 // --- spawn manifest (#341: codified/replayable orchestration) ---COMMENT
Excessive Try-Catch Wrapping15 hits · 18 pts
SeverityFileLineSnippetContext
LOWscripts/gasp_shim.sh417 except Exception as e: # one broken stream must not stop the othersCODE
LOWscripts/gasp_shim.sh453except Exception as e:CODE
LOWscripts/yoyo_context.sh73except Exception as e:CODE
MEDIUMscripts/format_discussions.py243 print(f"Error: REPO must be in 'owner/name' format, got: '{repo}'", file=sys.stderr)CODE
MEDIUMscripts/format_discussions.py249 print(f"Error: invalid repo format: '{repo}'", file=sys.stderr)CODE
MEDIUMscripts/format_discussions.py312 print("Error: repository not found in GraphQL response", file=sys.stderr)STRING
LOWscripts/evolve.sh314except Exception as exc:CODE
LOWscripts/evolve.sh938except Exception: print(0)' 2>/dev/null || echo 0)CODE
LOWscripts/evolve.sh1045except Exception as e:CODE
LOWscripts/evolve.sh1057 except Exception:CODE
LOWscripts/evolve.sh3031except Exception:CODE
LOWscripts/create_address_book.sh125except Exception as e:CODE
MEDIUMscripts/create_address_book.sh126 print(f'Error checking for existing Address Book: {e}', file=sys.stderr)CODE
LOWscripts/bench/humaneval_one.sh241except Exception as exc: # syntax error, import error, etc.CODE
LOWscripts/bench/humaneval_one.sh308 except Exception as exc:CODE
Verbosity Indicators9 hits · 14 pts
SeverityFileLineSnippetContext
LOWsrc/commands_update.rs99 // Step 1: Check for latest versionCOMMENT
LOWsrc/commands_update.rs137 // Step 2: Detect platform and find the right assetCOMMENT
LOWsrc/commands_update.rs167 // Step 3: Confirm with userCOMMENT
LOWsrc/commands_update.rs182 // Step 4: DownloadCOMMENT
LOWsrc/commands_update.rs205 // Step 5: Extract and replace. The extract dir is per-run, and createdCOMMENT
LOWsrc/setup.rs364 // Step 1: Choose providerCOMMENT
LOWsrc/setup.rs402 // Step 2: API key (skip for ollama, special flow for bedrock)COMMENT
LOWsrc/setup.rs592 // Step 3: Model preferenceCOMMENT
LOWsrc/setup.rs630 // Step 4: Offer to save config (three choices)COMMENT
Structural Annotation Overuse9 hits · 14 pts
SeverityFileLineSnippetContext
LOWsrc/commands_update.rs99 // Step 1: Check for latest versionCOMMENT
LOWsrc/commands_update.rs137 // Step 2: Detect platform and find the right assetCOMMENT
LOWsrc/commands_update.rs167 // Step 3: Confirm with userCOMMENT
LOWsrc/commands_update.rs182 // Step 4: DownloadCOMMENT
LOWsrc/commands_update.rs205 // Step 5: Extract and replace. The extract dir is per-run, and createdCOMMENT
LOWsrc/setup.rs364 // Step 1: Choose providerCOMMENT
LOWsrc/setup.rs402 // Step 2: API key (skip for ollama, special flow for bedrock)COMMENT
LOWsrc/setup.rs592 // Step 3: Model preferenceCOMMENT
LOWsrc/setup.rs630 // Step 4: Offer to save config (three choices)COMMENT
Deep Nesting16 hits · 13 pts
SeverityFileLineSnippetContext
LOWscripts/measure_abstentions.py735CODE
LOWscripts/check_assertion_weakening.py225CODE
LOWscripts/check_assertion_weakening.py349CODE
LOWscripts/check_assertion_weakening.py576CODE
LOWscripts/format_discussions.py491CODE
LOWscripts/scan_commitments.py219CODE
LOWscripts/scan_commitments.py288CODE
LOWscripts/lint_evolve_heredocs.py45CODE
LOWscripts/build_site.py52CODE
LOWscripts/refresh_sponsors.py331CODE
LOWscripts/format_issues.py133CODE
LOWscripts/extract_trajectory.py176CODE
LOWscripts/extract_trajectory.py1031CODE
LOWscripts/extract_trajectory.py1240CODE
LOWscripts/extract_trajectory.py1458CODE
LOWscripts/extract_trajectory.py1481CODE
Example Usage Blocks7 hits · 10 pts
SeverityFileLineSnippetContext
LOWscripts/yoyo_context.sh5# Usage:COMMENT
LOWscripts/reset_day.sh4# Usage:COMMENT
LOWscripts/evolve.sh7# Usage:COMMENT
LOWscripts/social.sh7# Usage:COMMENT
LOWscripts/evolve-local.sh4# Usage:COMMENT
LOWscripts/create_address_book.sh11# Usage:COMMENT
LOWscripts/run_mutants.sh4# Usage:COMMENT
Fake / Example Data11 hits · 10 pts
SeverityFileLineSnippetContext
LOWtests/integration.rs1836 .env("ANTHROPIC_API_KEY", "sk-test-fake-key")CODE
LOWtests/integration.rs1896 .env("ANTHROPIC_API_KEY", "sk-test-fake-key")CODE
LOWsrc/commands_git_review.rs1087 assert!(colored.contains("John Doe"));CODE
LOWsrc/commands_skill.rs1620 "test@test.com",CODE
LOWsrc/commands_info.rs2567 run(&["config", "user.email", "test@test.com"]);CODE
LOWsrc/commands_info.rs2918 .args(["config", "user.email", "test@test.com"])CODE
LOWsrc/prompt_retry.rs1754 std::env::set_var(key, "fake-key");CODE
LOWsrc/commands_git.rs2687 .args(["config", "user.email", "test@test.com"])CODE
LOWsrc/commands_revisit.rs1055 out.contains("(issue #999999)") && out.contains("placeholder"),CODE
LOWsrc/commands_spawn.rs3160 .args(["config", "user.email", "test@test.com"])CODE
LOWsrc/commands_file.rs2032 .args(["config", "user.email", "test@test.com"])CODE
Synthetic Comment Markers1 hit · 8 pts
SeverityFileLineSnippetContext
HIGHCLAUDE.md218- `git_commit_msg.rs` — the deterministic, token-free commit-message generator behind `/commit` (`generate_commit_messagCODE
Unused Imports3 hits · 3 pts
SeverityFileLineSnippetContext
LOWscripts/skill_evolve_report.py22CODE
LOWscripts/skill_evolve_report.py23CODE
LOWscripts/check_assertion_weakening.py50CODE
Redundant / Tautological Comments2 hits · 3 pts
SeverityFileLineSnippetContext
LOWscripts/evolve.sh1282# Check if assessment was producedCOMMENT
LOWscripts/evolve.sh1568# Check if planning agent produced tasksCOMMENT
Self-Referential Comments1 hit · 2 pts
SeverityFileLineSnippetContext
MEDIUMsrc/setup.rs99 config.push_str("# This file contains a secret — keep it out of version control.\n");CODE