3.1

Adjusted Signal

3.1

Raw Pattern Score

100%

Time Factor

2026-10-31

Last Push

11.7K

Stars

TypeScript

Language

40.9K

Lines of Code

506

Files

Pattern Hits

2026-10-31

Scan Date

0.01

HC Hit Rate

Risk Review · Payload v1

Use each vector to guide manual verification of the underlying findings.

Payload schema: 1.0.0 · Engine: 2.0.0 · Scoring: heuristic-density-v1 · Scan date: 2026-10-31.

Cognitive Ownership Risk 5.8/100 · LOW

Can maintainers explain intent, assumptions, and trade-offs? 22 finding(s).

Hallucinated Dependency & Supply Chain Risk 0.4/100 · LOW

Are imports declared and package/API names verified? 3 finding(s).

Agent Over-Engineering Ratio 9.2/100 · LOW

Are wrappers, guards, and repeated structures necessary? 26 finding(s).

PR Review Velocity Impact 15.5/100 · LOW

Which changes need focused human review? 46 finding(s).

What These Metrics Mean

Adjusted Signal: Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score: Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor: A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits: Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate: High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files: Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.

Severity Breakdown

Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.

CRITICAL 0HIGH 6MEDIUM 31LOW 9

Directory Score Breakdown

This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.

Pattern Findings

The scanner identified 46 distinct pattern matches across 7 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. 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 configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Decorative Section Separators15 hits · 44 pts

Severity	File	Line	Snippet	Context
MEDIUM	tools/loop-drill/src/drill.ts	109	// ── Glob → concrete sample path ────────────────────────────────────	COMMENT
MEDIUM	tools/loop-drill/src/drill.ts	135	// ── Gate drills (Over-Reach) ───────────────────────────────────────	COMMENT
MEDIUM	tools/loop-drill/src/drill.ts	265	// ── Circuit breaker drills (Infinite Fix Loop / Token Burn) ────────	COMMENT
MEDIUM	tools/loop-drill/src/drill.ts	458	// ── Report assembly ────────────────────────────────────────────────	COMMENT
MEDIUM	tools/mcp-server/src/index.ts	34	// ── Resources ──────────────────────────────────────────────────────	COMMENT
MEDIUM	tools/mcp-server/src/index.ts	138	// ── Resource Templates (dynamic) ───────────────────────────────────	COMMENT
MEDIUM	tools/mcp-server/src/index.ts	200	// ── Tools ──────────────────────────────────────────────────────────	COMMENT
MEDIUM	tools/mcp-server/src/index.ts	549	// ── Start ──────────────────────────────────────────────────────────	COMMENT
MEDIUM	tools/loop-context/src/context-manager.ts	85	// ── Config validation ──────────────────────────────────────────────	COMMENT
MEDIUM	tools/loop-context/src/context-manager.ts	129	// ── Error normalization ────────────────────────────────────────────	COMMENT
MEDIUM	tools/loop-context/src/context-manager.ts	180	// ── Circuit breaker ────────────────────────────────────────────────	COMMENT
MEDIUM	tools/loop-context/src/context-manager.ts	316	// ── Pruning ────────────────────────────────────────────────────────	COMMENT
MEDIUM	tools/loop-context/src/context-manager.ts	364	// ── Summarization ──────────────────────────────────────────────────	COMMENT
MEDIUM	tools/loop-context/src/context-manager.ts	427	// ── Injection ──────────────────────────────────────────────────────	COMMENT
MEDIUM	…ources/ky-cut-surface-philosophy-v0_1/TERMINAL_ART.txt	1	┌──[ KUNST-TERMINALEN // KY CUT SURFACE v0.1 ]──────────────────────────────┐	CODE

Modern AI Meta-Vocabulary13 hits · 34 pts

Severity	File	Line	Snippet	Context
MEDIUM	tools/loop-swarm/README.md	18	See [Quickstart](../../docs/QUICKSTART.md#multi-agent-consensus-sandboxing-loop-swarm) for workflow examples and command	CODE
MEDIUM	tools/loop-sync/README.md	52	# Preview what --auto-fix would scaffold/change, without writing anything	COMMENT
MEDIUM	tools/loop-audit/src/auditor.ts	887	// Proof that guardrails fire, from loop-drill --record.	COMMENT
MEDIUM⚡	tools/loop-audit/src/cli.ts	99	console.log(' # Or scaffold automatically:');	CODE
MEDIUM⚡	tools/loop-audit/src/cli.ts	108	console.log(' # IMPORTANT (v1.4): After scaffolding, actually RUN a loop (report-only) and commit the updated STATE	CODE
MEDIUM⚡	tools/loop-audit/src/cli.ts	111	console.log(' # L3: prove the guardrails fire, not just exist, then commit the record');	CODE
MEDIUM	docs/QUICKSTART.md	17	Not sure which loop? Use the [interactive pattern picker](https://cobusgreyling.github.io/loop-engineering/#interactive)	CODE
MEDIUM	docs/QUICKSTART.md	17	Not sure which loop? Use the [interactive pattern picker](https://cobusgreyling.github.io/loop-engineering/#interactive)	CODE
MEDIUM	docs/QUICKSTART.md	355	# Run multi-agent consensus across 3 sequential sandboxes	COMMENT
MEDIUM	docs/safety.md	136	- `loop-swarm`: Multi-agent consensus sandboxing across sequential `loop-sandbox` runs. Requires byte-identical patch co	CODE
MEDIUM	docs/RELEASE.md	104	# goal-init (scaffold goal engineering setups)	COMMENT
MEDIUM	examples/codex/issue-triage.md	36	Install `issue-triage` per [Codex Agent Skills](https://developers.openai.com/codex/skills) — scaffold with `loop-init`	CODE
MEDIUM	examples/github-actions/ci-sweeper.yml	1	# CI Sweeper — event-driven on workflow failure	COMMENT

Cross-File Repetition6 hits · 30 pts

Severity	File	Snippet	Context
HIGH	starters/minimal-loop-codex/.codex/agents/verifier.toml	you are the checker in a maker/checker split. default stance: reject until proven otherwise. checklist (all must pass fo	STRING
HIGH	starters/ci-sweeper/.codex/agents/verifier.toml	you are the checker in a maker/checker split. default stance: reject until proven otherwise. checklist (all must pass fo	STRING
HIGH	starters/pr-babysitter/.codex/agents/verifier.toml	you are the checker in a maker/checker split. default stance: reject until proven otherwise. checklist (all must pass fo	STRING
HIGH	starters/issue-triage/.codex/agents/verifier.toml	you are the checker in a maker/checker split. default stance: reject until proven otherwise. checklist (all must pass fo	STRING
HIGH	starters/post-merge-cleanup/.codex/agents/verifier.toml	you are the checker in a maker/checker split. default stance: reject until proven otherwise. checklist (all must pass fo	STRING
HIGH	starters/dependency-sweeper/.codex/agents/verifier.toml	you are the checker in a maker/checker split. default stance: reject until proven otherwise. checklist (all must pass fo	STRING

AI Slop Vocabulary3 hits · 9 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tools/loop-audit/src/cli.ts	105	console.log(' # or: npx @cobusgreyling/harness-foundry init --from loop-engineering:daily-triage');	CODE
MEDIUM	examples/github-actions/daily-triage.yml	2	# Invokes your agent harness with a triage prompt. Adapt the "Run agent" step	COMMENT
MEDIUM	examples/github-actions/issue-triage.yml	3	# issue-triage-state.md. Wire the "Run triage agent" step to your harness.	COMMENT

Hyper-Verbose Identifiers5 hits · 5 pts

Severity	File	Line	Snippet	Context
LOW	tools/loop-init/src/cli.ts	254	function cheaperinferenceInterfaceYaml(model: string): string {	CODE
LOW	tools/loop-context/src/budget-resolver.ts	13	export function assertValidBudgetScenario(scenario: string): asserts scenario is BudgetScenario {	CODE
LOW	tools/loop-context/src/budget-resolver.ts	106	export async function resolveTokenBudgetFromPattern(input: BudgetFromPatternInput): Promise<number> {	CODE
LOW	tools/loop-context/src/budget-resolver.ts	126	export async function resolveDailyBudgetFromPattern(input: BudgetFromPatternInput): Promise<number> {	CODE
LOW	tools/loop-context/src/context-manager.ts	95	export function assertSimilarityThreshold(value: unknown, label = 'similarityThreshold'): asserts value is number {	CODE

Unused Imports3 hits · 3 pts

Severity	File	Line	Context
LOW	scripts/generate-star-history.py	13	CODE
LOW	scripts/generate-audit-demo-gif.py	4	CODE
LOW	scripts/generate-audit-demo-gif.py	7	CODE

Over-Commented Block1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	tools/loop-sandbox/src/sandbox.ts	81	// Cleanup must run on every exit path, including Ctrl+C mid-run, and	COMMENT

cobusgreyling/loop-engineering

Open-Source Code Quality, Security and Technical Debt Review