Repository Analysis

Gentleman-Programming/engram

Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.

9.9 Low AI signal View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of Gentleman-Programming/engram, a Go project with 6,268 GitHub stars. SynthScan v2.0 examined 192,713 lines of code across 485 source files, recording 708 pattern matches distributed across 8 syntactic categories. The overall adjusted score of 9.9 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).

9.9
Adjusted Score
9.9
Raw Score
100%
Time Factor
2026-09-02
Last Push
6.3K
Stars
Go
Language
192.7K
Lines of Code
485
Files
708
Pattern Hits
2026-09-02
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

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

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 0MEDIUM 582LOW 126

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 708 distinct pattern matches across 8 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 Separators574 hits · 1722 pts
SeverityFileLineSnippetContext
MEDIUMcmd/engram/conflicts_test.go25// ─── mock runner for D.2 tests ────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/conflicts_test.go61// ─── helpers ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/conflicts_test.go151// ─── D.1 RED tests ────────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/conflicts_test.go534// ─── G.1 — End-to-end CLI lifecycle integration tests ────────────────────────COMMENT
MEDIUMcmd/engram/conflicts_test.go666// ─── D.2 RED tests — agentRunnerFactory + resolveAgentRunner ─────────────────COMMENT
MEDIUMcmd/engram/autosync_status_test.go40// ─── Status adapter tests (REQ-209) ──────────────────────────────────────────COMMENT
MEDIUMcmd/engram/llm.go12// ─── agentRunnerFactory default ───────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/llm.go26// ─── llmRunnerAdapter ─────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/llm.go52// ─── llmBuildPrompt ───────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/llm.go64// ─── resolveAgentRunner ───────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/conflicts.go62// ─── list ─────────────────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/conflicts.go164// ─── show ─────────────────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/conflicts.go225// ─── stats ────────────────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/conflicts.go291// ─── scan ─────────────────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/conflicts.go510// ─── deferred ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/main.go777// ─── Commands ────────────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/main.go3019// ─── Helpers ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/autosync_e2e_test.go21// ─── E2E Round-trip test (REQ-212) ───────────────────────────────────────────COMMENT
MEDIUMcmd/engram/autosync_e2e_test.go246// ─── Fake store for E2E tests ─────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/main_test.go1359// ─── Projects command tests ───────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/main_test.go2400// ─── obsidian-export command tests ───────────────────────────────────────────COMMENT
MEDIUMcmd/engram/main_test.go2535// ─── obsidian-export Phase 4 tests (graph-config, watch, interval) ───────────COMMENT
MEDIUMcmd/engram/main_test.go2769// ─── Delete command tests ─────────────────────────────────────────────────────COMMENT
MEDIUMcmd/engram/main_test.go2869// ─── delete session sub-command tests ─────────────────────────────────────────COMMENT
MEDIUMcmd/engram/main_test.go2951// ─── delete prompt sub-command tests ──────────────────────────────────────────COMMENT
MEDIUMcmd/engram/main_test.go3021// ─── delete project sub-command tests ─────────────────────────────────────────COMMENT
MEDIUMcmd/engram/main_test.go3087// ─── backward-compat: delete <obs_id> still works ─────────────────────────────COMMENT
MEDIUMcmd/engram/main_test.go3103// ─── usage shows new sub-commands ─────────────────────────────────────────────COMMENT
MEDIUMplugin/claude-code/scripts/user-prompt-submit.sh410# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/claude-code/scripts/user-prompt-submit.sh417# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/claude-code/scripts/user-prompt-submit.sh434# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/claude-code/scripts/user-prompt-submit.sh439# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/claude-code/scripts/user-prompt-submit.sh452 # ── FIRST MESSAGE ────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/claude-code/scripts/user-prompt-submit.sh461# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/claude-code/scripts/user-prompt-submit.sh463# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/codex/scripts/user-prompt-submit.sh33# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/codex/scripts/user-prompt-submit.sh40# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/codex/scripts/user-prompt-submit.sh92# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/codex/scripts/user-prompt-submit.sh97# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/codex/scripts/user-prompt-submit.sh109 # ── FIRST MESSAGE ────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/codex/scripts/user-prompt-submit.sh118# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/codex/scripts/user-prompt-submit.sh120# ──────────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/main.ts10// ─── Plugin ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/main.ts24 // ─── Lifecycle ────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/main.ts69 // ─── Settings ─────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/main.ts80 // ─── Auto-sync ────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/main.ts118 // ─── Sync ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/main.ts134 // ── Failure path ────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/main.ts145 // ── Success path ──────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/main.ts169 // ─── Status Bar ───────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/settings.ts4// ─── Settings Interface ────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/settings.ts30// ─── Settings Tab ─────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/settings.ts50 // ── Engram URL ──────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/settings.ts95 // ── Auto-sync Interval ──────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/settings.ts118 // ── Project Filter ──────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/settings.ts134 // ── Vault Subfolder ─────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/settings.ts151 // ── Manual Sync Button ──────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/settings.ts189// ─── Helpers ──────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/sync.ts4// ─── API Types ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMplugin/obsidian/src/sync.ts25// ─── Sync State ───────────────────────────────────────────────────────────────COMMENT
514 more matches not shown…
Over-Commented Block72 hits · 62 pts
SeverityFileLineSnippetContext
LOWdocker-compose.beta.yml1# Engram Beta — Phases 2 + 3 + 4 community testingCOMMENT
LOWDOCS.md701# source-run flow (without compose): set BOTH token + allowlist before startupCOMMENT
LOWcmd/engram/cloud.go121 }COMMENT
LOWcmd/engram/cloud.go141// credentials, but PrincipalResolver.ResolveBearerToken (foundation.go)COMMENT
LOWcmd/engram/cloud_bootstrap.go21 cloudBootstrapAuditOutcomeSuccess = "success"COMMENT
LOWcmd/engram/cloud_runtime_auth.go21// actually checks the legacy credentials FIRST and only falls back toCOMMENT
LOWcmd/engram/cloud_runtime_auth.go41// s.auth.Authorize when s.auth does NOT implement ResolveBearerToken; sinceCOMMENT
LOWcmd/engram/cloud_runtime_auth.go61// cloudstoreManagedTokenLookup depends on. *cloudstore.CloudStore satisfiesCOMMENT
LOWcmd/engram/cloud_runtime_e2e_test.go61// real HTTP requests through the assembled *cloudserver.CloudServer, proving:COMMENT
LOWcmd/engram/cloud_runtime_auth_test.go101}COMMENT
LOWtools/repair-missing-session-directory.sh1#!/usr/bin/env bashCOMMENT
LOWplugin/claude-code/scripts/user-prompt-submit.sh1#!/usr/bin/env bashCOMMENT
LOWplugin/codex/scripts/user-prompt-submit.sh1#!/usr/bin/env bashCOMMENT
LOWplugin/codex/scripts/subagent-stop.sh1#!/usr/bin/env bashCOMMENT
LOWinternal/llm/runner.go1// Package llm defines the AgentRunner abstraction used by Engram to delegateCOMMENT
LOWinternal/llm/runner.go21// structured Verdict.COMMENT
LOWinternal/llm/claude.go21 runCLI func(ctx context.Context, name string, args []string, stdin string) ([]byte, error)COMMENT
LOWinternal/llm/cost.go1package llmCOMMENT
LOWinternal/llm/cost.go21// EstimateScanCost returns the estimated total input and output token countsCOMMENT
LOWinternal/llm/prompt.go21}COMMENT
LOWinternal/diagnostic/checks.go221 // work that still needs a decision rather than already-dispositioned evidence.COMMENT
LOWinternal/setup/generate.go1package setupCOMMENT
LOWinternal/setup/protocol.go41 return normalizeProtocolMode(mode)COMMENT
LOWinternal/setup/registry.go21const (COMMENT
LOWinternal/setup/setup.go1// Package setup handles agent plugin installation.COMMENT
LOWinternal/setup/setup.go361COMMENT
LOWinternal/setup/setup.go501// patchEngramBINLine rewrites the ENGRAM_BIN constant declaration in theCOMMENT
LOWinternal/mcp/mcp_test.go7521// TestHandleSave_MCPConfig_OverridesDefaults verifies that MCPConfig.BM25FloorCOMMENT
LOWinternal/mcp/mcp_conflict_loop_test.go421 }COMMENT
LOWinternal/mcp/mcp.go1// Package mcp implements the Model Context Protocol server for Engram.COMMENT
LOWinternal/mcp/mcp.go41 // auto-resolution; per-call project arguments remain separately validated.COMMENT
LOWinternal/mcp/mcp.go101 if strings.TrimSpace(directory) == "" {COMMENT
LOWinternal/mcp/serverinstructions_length_test.go1package mcpCOMMENT
LOWinternal/project/detect.go41 SourceUserSelectedAfterAmbiguousProject = "user_selected_after_ambiguous_project"COMMENT
LOWinternal/cloud/cloudstore/identity_storage_test.go681// TestFindPrincipalTokenByHashResolvesActiveTokenAndRejectsUnknownOrRevokedCOMMENT
LOWinternal/cloud/cloudstore/identity.go281// guardLastActiveAdminTx (key "engram_cloud_active_admin_guard"). ThisCOMMENT
LOWinternal/cloud/cloudstore/identity.go681// internal/cloud/auth already imports cloudstore and a direct cloudstore ->COMMENT
LOWinternal/cloud/autosync/manager.go1// Package autosync implements a lease-guarded background sync managerCOMMENT
LOWinternal/cloud/cloudserver/dashboard_session.go161 }COMMENT
LOWinternal/cloud/cloudserver/dashboard_session.go201 log.Printf("[engram-cloud] dashboard login audit insert failed (best-effort): %v", err)COMMENT
LOWinternal/cloud/cloudserver/dashboard_session.go561 if source := string(actor.Source); source != "" {COMMENT
LOWinternal/cloud/cloudserver/dashboard_admin_users.go21// (requireManagedAdmin), and SAME audit path (recordAdminAudit) alreadyCOMMENT
LOWinternal/cloud/cloudserver/dashboard_admin_users.go81// renderDashboardAdminComponentStatus is renderDashboardAdminComponent butCOMMENT
LOWinternal/sync/transport.go21 // WriteManifest persists the manifest.COMMENT
LOWinternal/sync/sync.go1// Package sync implements git-friendly memory synchronization for Engram.COMMENT
LOWinternal/sync/sync_test.go1041 }COMMENT
LOWinternal/store/store_migration_test.go401COMMENT
LOWinternal/store/store_migration_test.go541 missing = append(missing, req)COMMENT
LOWinternal/store/store_legacy_ddl_test.go1package storeCOMMENT
LOWinternal/store/store_legacy_ddl_test.go221 VALUES (new.id, new.content, new.project);COMMENT
LOWinternal/store/store_test.go6581 }COMMENT
LOWinternal/store/store_test.go10561 }COMMENT
LOWinternal/store/store.go1221 // This runs on every open rather than only in the open that added the column.COMMENT
LOWinternal/store/store.go2461// such a session exists, or ok=false when none does.COMMENT
LOWinternal/store/store.go5281// relation mutation. The two apply statuses record different things and so carryCOMMENT
LOWinternal/store/store.go5601 // parent session belongs to another project, so moving it would split it.COMMENT
LOWinternal/store/store.go6461}COMMENT
LOWinternal/store/store.go7201// Design mirrors backfillObservationSyncMutationsTx exactly:COMMENT
LOWinternal/store/store.go7581}COMMENT
LOWinternal/store/store.go7641}COMMENT
12 more matches not shown…
Structural Annotation Overuse25 hits · 46 pts
SeverityFileLineSnippetContext
LOWCONTRIBUTING.md13### Step 1: Open an IssueCOMMENT
LOWCONTRIBUTING.md23### Step 2: Wait for ApprovalCOMMENT
LOWCONTRIBUTING.md29### Step 3: Open a Pull RequestCOMMENT
LOWCONTRIBUTING.md38### Step 4: Automated PR ChecksCOMMENT
LOWinternal/tui/update_test.go960 // Step 1: from SearchResults, enter ObservationDetail — PrevScreen = ScreenSearchResultsCOMMENT
LOWinternal/tui/update_test.go969 // Step 2: from ObservationDetail, Esc → back to SearchResults (via PrevScreen)COMMENT
LOWinternal/tui/update_test.go978 // Step 3: from SearchResults, Esc → back to ScreenSearch, PrevScreen reset to DashboardCOMMENT
LOWinternal/tui/update_test.go989 // Step 4: from Search (no input focused), Esc → always Dashboard, never loopsCOMMENT
LOWinternal/tui/update_test.go997 // Step 5: from Search input focused, Esc → always Dashboard, never loopsCOMMENT
LOWinternal/setup/setup.go811 // Step 1: Add marketplace (idempotent — if already added, claude will say so)COMMENT
LOWinternal/setup/setup.go821 // Step 2: Install the pluginCOMMENT
LOWinternal/setup/setup.go831 // Step 3: Write a durable user-level MCP config at ~/.claude/mcp/engram.jsonCOMMENT
LOWinternal/setup/setup.go1207 // Step 1: add the marketplace (idempotent — tolerate "already" in output).COMMENT
LOWinternal/setup/setup.go1214 // Step 2: install the plugin (idempotent — tolerate "already" in output).COMMENT
LOWinternal/cloud/cloudserver/cloudserver_test.go1459 // Step 1: POST to mutation push with paused project → should 409 + emit audit.COMMENT
LOWinternal/cloud/cloudserver/cloudserver_test.go1475 // Step 2: verify audit row was captured in the store.COMMENT
LOWinternal/cloud/cloudserver/cloudserver_test.go1487 // Step 3: list via the store's audit method (simulates what the dashboard handler would call).COMMENT
LOWinternal/sync/sync.go1695 // Step 1: index sessions that match by their own projectCOMMENT
LOWinternal/sync/sync.go1704 // Step 2: observations — match by own project OR by sessionCOMMENT
LOWinternal/sync/sync.go1720 // Step 3: prompts — match by own project OR by sessionCOMMENT
LOWinternal/sync/sync.go1735 // Step 4: include sessions that matched directly or are referenced by included entitiesCOMMENT
LOWinternal/store/store.go7713 // Step 1: decode payload.COMMENT
LOWinternal/store/store.go7759 // Step 2: FK precondition — both observations must exist locally (by sync_id).COMMENT
LOWinternal/store/store.go7775 // Step 3: upsert into memory_relations keyed on sync_id (idempotent re-apply).COMMENT
LOWinternal/store/store.go7804 // Step 4: clean up the rows this relation left behind (its pending retryCOMMENT
Verbosity Indicators21 hits · 38 pts
SeverityFileLineSnippetContext
LOWinternal/tui/update_test.go960 // Step 1: from SearchResults, enter ObservationDetail — PrevScreen = ScreenSearchResultsCOMMENT
LOWinternal/tui/update_test.go969 // Step 2: from ObservationDetail, Esc → back to SearchResults (via PrevScreen)COMMENT
LOWinternal/tui/update_test.go978 // Step 3: from SearchResults, Esc → back to ScreenSearch, PrevScreen reset to DashboardCOMMENT
LOWinternal/tui/update_test.go989 // Step 4: from Search (no input focused), Esc → always Dashboard, never loopsCOMMENT
LOWinternal/tui/update_test.go997 // Step 5: from Search input focused, Esc → always Dashboard, never loopsCOMMENT
LOWinternal/setup/setup.go811 // Step 1: Add marketplace (idempotent — if already added, claude will say so)COMMENT
LOWinternal/setup/setup.go821 // Step 2: Install the pluginCOMMENT
LOWinternal/setup/setup.go831 // Step 3: Write a durable user-level MCP config at ~/.claude/mcp/engram.jsonCOMMENT
LOWinternal/setup/setup.go1207 // Step 1: add the marketplace (idempotent — tolerate "already" in output).COMMENT
LOWinternal/setup/setup.go1214 // Step 2: install the plugin (idempotent — tolerate "already" in output).COMMENT
LOWinternal/cloud/cloudserver/cloudserver_test.go1459 // Step 1: POST to mutation push with paused project → should 409 + emit audit.COMMENT
LOWinternal/cloud/cloudserver/cloudserver_test.go1475 // Step 2: verify audit row was captured in the store.COMMENT
LOWinternal/cloud/cloudserver/cloudserver_test.go1487 // Step 3: list via the store's audit method (simulates what the dashboard handler would call).COMMENT
LOWinternal/sync/sync.go1695 // Step 1: index sessions that match by their own projectCOMMENT
LOWinternal/sync/sync.go1704 // Step 2: observations — match by own project OR by sessionCOMMENT
LOWinternal/sync/sync.go1720 // Step 3: prompts — match by own project OR by sessionCOMMENT
LOWinternal/sync/sync.go1735 // Step 4: include sessions that matched directly or are referenced by included entitiesCOMMENT
LOWinternal/store/store.go7713 // Step 1: decode payload.COMMENT
LOWinternal/store/store.go7759 // Step 2: FK precondition — both observations must exist locally (by sync_id).COMMENT
LOWinternal/store/store.go7775 // Step 3: upsert into memory_relations keyed on sync_id (idempotent re-apply).COMMENT
LOWinternal/store/store.go7804 // Step 4: clean up the rows this relation left behind (its pending retryCOMMENT
Modern AI Meta-Vocabulary6 hits · 17 pts
SeverityFileLineSnippetContext
MEDIUMdocs/ARCHITECTURE.md237├── skills/ # Contributor AI skills (repo-wide standards + Engram-specific guardrails)CODE
MEDIUMdocs/codebase/sync-and-cloud.md106## Sync/cloud guardrailsCOMMENT
MEDIUM…chive/2026-04-24-memory-conflict-surfacing/proposal.md447### 6.5 Boundary/regression tests (per `engram-server-api`, `engram-architecture-guardrails`)COMMENT
MEDIUM…ges/archive/2026-04-27-memory-conflict-audit/design.md53### 1.2 Boundaries (engram-architecture-guardrails)COMMENT
MEDIUMopenspec/changes/memory-conflict-surfacing/proposal.md447### 6.5 Boundary/regression tests (per `engram-server-api`, `engram-architecture-guardrails`)COMMENT
MEDIUMopenspec/changes/memory-conflict-audit/design.md53### 1.2 Boundaries (engram-architecture-guardrails)COMMENT
Self-Referential Comments2 hits · 9 pts
SeverityFileLineSnippetContext
MEDIUMplugin/claude-code/scripts/user-prompt-submit.sh453 # Create the state file immediately to prevent repeat injectionsCOMMENT
MEDIUMplugin/codex/scripts/user-prompt-submit.sh110 # Create the state file immediately to prevent repeat injectionsCOMMENT
Hyper-Verbose Identifiers7 hits · 7 pts
SeverityFileLineSnippetContext
LOWplugin/pi/index.ts185function takeLastFetchTimeoutMethod(): string | undefined {CODE
LOWplugin/pi/index.ts300function projectCurrentUnsupportedError(cwd: string): CurrentProjectResponse {CODE
LOWplugin/pi/index.ts729function normalizeInitializationError(error: unknown): Error {CODE
LOWplugin/opencode/engram.ts277 function isKnownAuthoritativeRootSession(sessionId: string): boolean {CODE
LOWplugin/opencode/engram.ts333 async function resolveAuthoritativeSessionID(sessionId: string): Promise<string> {CODE
LOWinternal/setup/plugins/opencode/engram.ts277 function isKnownAuthoritativeRootSession(sessionId: string): boolean {CODE
LOWinternal/setup/plugins/opencode/engram.ts333 async function resolveAuthoritativeSessionID(sessionId: string): Promise<string> {CODE
Example Usage Blocks1 hit · 2 pts
SeverityFileLineSnippetContext
LOWdocker-compose.beta.yml7# Usage:COMMENT