Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HuginnIndustries/CodeCartographer --skill defect-scan-mechanicalgit clone --depth 1 https://github.com/HuginnIndustries/CodeCartographerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huginnindustries/codecartographer/defect-scan-mechanical)<a href="https://agentmods.dev/skills/huginnindustries/codecartographer/defect-scan-mechanical"><img src="https://agentmods.dev/badge/skills/huginnindustries/codecartographer/defect-scan-mechanical.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.00953 |
| Opus 5 | $0.00044 | $0.00477 |
| Sonnet 5 | $0.00018 | $0.00191 |
| Haiku 4.5 | $0.00009 | $0.00095 |
Grade A, and why
scan-for-defects-mechanical scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan For Defects — Mechanical Pass
This phase runs the early, mechanical half of the defect-scan methodology. It catches the bugs that are visible from local code reading without needing the contracts or protocols phases to be done first. The deeper passes (concurrency, security, API contract violations) live in the later defect-scan-semantic phase.
The source code to analyze is in the parent directory (../ relative to .codecarto/).
Prerequisites
Required:
findings/architecture/architecture-map.md— for the layer map and public surfaces.
You do not need contracts or protocols for this phase. If those exist already, skim them as bonus context, but do not block on them — the mechanical pass is by design context-light.
Pass Execution Order
Run these three passes sequentially. Read the pass file, scan the source, record findings, then move to the next pass. Each pass file is the same one used by the legacy defect-scan phase — only the subset is different.
| Pass | File | Focus |
|---|---|---|
| 1 | findings/defect-scan/passes/01-logic-and-correctness.md |
Dead code, boundary errors, null handling, boolean logic, control flow |
| 2 | findings/defect-scan/passes/02-error-handling.md |
Swallowed errors, missing cleanup, uncaught exceptions, retry gaps |
| 6 | findings/defect-scan/passes/06-config-and-environment.md |
Hardcoded values, missing validation, dangerous defaults, OS assumptions |
Passes 3, 4, and 5 are deferred to defect-scan-semantic because they benefit from contracts/protocols context.
Prioritization
Use the architecture map to decide emphasis:
- Pure library with no config? Skim pass 6.
- Heavy generic-types or branching logic? Spend extra time on pass 1.
- No surfaced error model in architecture? Pass 2 may surface that gap as a finding.
Evidence and Severity Classification
Use the same scheme as the legacy defect-scan SKILL:
- Evidence levels:
observed fact,strong inference,external-behavior claim,open question. - Severity:
critical,high,medium,low. - Action (pre-porting pipelines):
fix before porting,port differently,leave behind,verify at runtime. - Pairing rule:
open questionorexternal-behavior claimevidence takesverify at runtimeorport differently, neverfix before porting, and the finding also appears in the report's Open Questions table. Validation checks this on the findings tables.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +1 lines 610fbe4bf54d
- 7d ago First seen · 61 lines · 88 tokens per session scan A 575ecd5727ae
scan-for-defects-mechanical is a skill published in the GitHub repository HuginnIndustries/CodeCartographer (4 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 953 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dx-audit
Audits libraries, CLIs, and SDKs using 38 rules for public contracts, package exports, piped output, errors, and configuration. Use when asked to "audit my CLI", "review my SDK", "make this agent-friendly", or diagnose package type resolution. For agentic product trust use ax-audit; for docs use docs-writing.
vibedrift-drift-check
Use when writing or changing code in an existing repository to keep new code consistent with the repo's own conventions and avoid duplicating code that already exists. Checks a proposed function against the repo's dominant patterns and existing functions BEFORE it lands, turning drift detection into drift prevention.…
perf
Performance optimizer for loops, DB queries, rendering, and batch operations. Catches N+1 queries, missing indexes, and unnecessary re-renders.
knip
Find dead code, unused files, unused exports, and unused dependencies in a JavaScript/TypeScript project using knip. Use before a refactor, before a PR, or when the user asks to clean up bloat, remove unused deps, or shrink the codebase.
proactive-analysis
Automatically run a tech-debt scan before opening a pull request, after large refactors, or when the user asks for a code review — surface actionable findings without being asked.
edge-case-hunter
Exhaustive edge-case review that traces branching paths and boundary conditions in a diff or code sample and reports only unhandled cases. Use when the user asks to hunt edge cases, boundary conditions, missing guards, or wants an edge-case-focused review.