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 3xachris/3xa-harness --skill repo-auditgit clone --depth 1 https://github.com/3xachris/3xa-harnessWrote 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/3xachris/3xa-harness/repo-audit)<a href="https://agentmods.dev/skills/3xachris/3xa-harness/repo-audit"><img src="https://agentmods.dev/badge/skills/3xachris/3xa-harness/repo-audit/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/3xachris/3xa-harness/repo-audit"><img src="https://agentmods.dev/badge/skills/3xachris/3xa-harness/repo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00106 | $0.02417 |
| Opus 5 | $0.00053 | $0.01208 |
| Sonnet 5 | $0.00021 | $0.00483 |
| Haiku 4.5 | $0.00011 | $0.00242 |
Grade A, and why
repo-audit 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 11d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Audit
Records rot in the direction nobody is looking. A log grows past the size where tools read it whole; a source: points at a file that got renamed; the third local fix lands on a cause that deserved one real fix; a document stops being referenced and nobody notices it is now folklore. None of these announce themselves, and all of them are measurable.
The script repo_audit.py runs five such measurements and prints one report. It answers questions about form — does this resolve, is this over the line, how many times has this happened. It answers nothing about meaning, and says so in the report rather than leaving the reader to assume otherwise.
1. What it measures
| Check | Question | Reads |
|---|---|---|
| size | Is anything past the limit set for its class, and what grew since last time? | file sizes; the decision log against its own split threshold |
| pointers | Does every reference resolve? | source: keys in the log's YAML blocks, [[WikiLinks]] and their headings, | evidence: paths, relative Markdown links |
| corrections | Is one cause collecting patches instead of a fix? | correction and amendment entries in the log, grouped by root_cause or tag |
| signals | Where does the code carry the shapes debt travels in? | swallowed exceptions, disabled checks, temporary markers, hand-sync comments, dates baked into shared constants, deprecated-but-imported modules |
| references | What has nothing referred to lately? | tracked documents against the set of files that would cite them |
Three of the five read this pack's own record formats and need them to exist. Size, pointers, and corrections resolve decision-log entries — the fenced YAML blocks, their source: keys, and type: correction with a root_cause or a tag. On a project with no such log they have nothing to read, and each says so by name in part 5 of the report rather than returning a clean result. Signals and references read generic file properties and work on any repository. Whether that split makes the tool worth having depends on which records your project actually keeps — the decision test in the README section Record audits is the place that question is answered, not here.
What ships with it
2 files 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.
- 11d ago First seen · 112 lines · 106 tokens per session scan A 58e8e2c8d149
repo-audit is a skill published in the GitHub repository 3xachris/3xa-harness (17 stars, last pushed 11d ago), licensed MIT. It adds 106 tokens to every session and 2,417 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
tech-debt-collector
Evidence-gated tech debt and bloat detection. Scouts signals, ranks by materiality, validates by refutation, reports up to 5 findings with actions.
code-comments
Extract comment locations from code files for analysis. Use when cleaning comments, auditing documentation, or analyzing comment patterns across languages.
code-investigate
Systematic investigation of bugs and issues to identify root causes through evidence-based analysis, hypothesis testing, and comprehensive documentation without permanent code changes.
fix-mermaid
Validates and repairs mermaid diagrams in markdown files. Scans for mermaid blocks, validates syntax, and auto-repairs common errors.
ph-debug
(PH) Use for a reproducible failure or unexpected behavior; reproduce, isolate, and verify the cause.
ph-lsp-setup
(PH) Use only when the user explicitly requests language-server setup or diagnostics.