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-semanticgit 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-semantic)<a href="https://agentmods.dev/skills/huginnindustries/codecartographer/defect-scan-semantic"><img src="https://agentmods.dev/badge/skills/huginnindustries/codecartographer/defect-scan-semantic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huginnindustries/codecartographer/defect-scan-semantic"><img src="https://agentmods.dev/badge/skills/huginnindustries/codecartographer/defect-scan-semantic.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00087 | $0.01213 |
| Opus 5.5 | $0.00035 | $0.00485 |
| Sonnet 5.5 | $0.00017 | $0.00243 |
| Haiku 4.5 | $0.00009 | $0.00121 |
Grade A, and why
scan-for-defects-semantic 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 1mo ago.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan For Defects — Semantic Pass
This phase runs the deep, semantic half of the defect-scan methodology. The findings here only become legible once you know what the code is supposed to do — that is what the contracts and protocols phases give you. The early mechanical bugs (passes 1, 2, 6) were caught in the earlier defect-scan-mechanical phase.
The source code to analyze is in the parent directory (../ relative to .codecarto/).
Prerequisites
Required:
findings/architecture/architecture-map.mdfindings/contracts/behavioral-contracts.md— pass 5 needs this to define "violation."findings/protocols/protocols-and-state.md— passes 3 and 5 need this for state machine and event-ordering analysis.findings/defect-scan-mechanical/mechanical-defects.md— read so you do not re-flag what the mechanical phase already covered.
Read when a finding turns on it: the source of a dependency the code trusts (under
node_modules/, the vendored tree, or the SDK's published source), at the pinned version. The
evidence rules allow "that system's own source" to settle an external-behavior claim about it,
and passes 4 and 5 keep meeting claims of that shape — what a lock does on release, what a
session runtime frees on dispose. Reading the pinned source is cheaper than a runtime probe and
turns the claim into an observed fact; say which file and version you read.
If any prerequisite is missing, stop and surface the gap. The semantic pass is the paid-for benefit of running the mechanical phase early; do not regress it by running the semantic pass blind.
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 reused from the legacy defect-scan phase.
| Pass | File | Focus |
|---|---|---|
| 3 | findings/defect-scan/passes/03-concurrency-and-resources.md |
Race conditions, lock issues, async pitfalls, resource leaks |
| 4 | findings/defect-scan/passes/04-security-and-trust.md |
Input validation, auth gaps, secrets in code, trust boundaries |
| 5 | findings/defect-scan/passes/05-api-contract-violations.md |
Spec vs. implementation drift, return type mismatches, state machine violations |
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.
- 1mo ago Changed · +7 lines 5bcb620bdaf8
- 1mo ago Changed · +2 lines 724d5e8a762c
- 1mo ago First seen · 55 lines · 87 tokens per session scan A f6509a00929d
scan-for-defects-semantic is a skill published in the GitHub repository HuginnIndustries/CodeCartographer (7 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 1,213 once invoked, about $0.0003 per session on Opus 5.5. 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
code-review
Reviews code for bugs, security issues, and best practices.
resolve-review-pr
Review an existing fix PR using the audited repro and full diff, preserving branch and approval rules.
ix
Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.
deep-analysis
Performs focused, depth-first investigation of specific reverse engineering questions through iterative analysis and database improvement. Answers questions like "What does this function do?", "Does this use crypto?", "What's the C2 address?", "Fix types in this function". Makes incremental improvements (renaming…
ctf-rev
Solve CTF reverse engineering challenges using systematic analysis to find flags, keys, or passwords. Use for crackmes, binary bombs, key validators, obfuscated code, algorithm recovery, or any challenge requiring program comprehension to extract hidden information.
pyghidra-scripting
Write and run Python (PyGhidra) code inside the Ghidra session that ReVa's MCP server is already attached to, using the five ReVa scripting tools — run-script, list-scripts, read-script, write-script, edit-script. Use this whenever the user asks to execute Python against the current program, reach for the Ghidra Flat…