Borrowing it
Nothing to install: this file belongs to tellahq/opensession. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tellahq/opensession/main/.agents/skills/audit-codebase/SKILL.mdgit clone --depth 1 https://github.com/tellahq/opensessionWrote 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/tellahq/opensession/audit-codebase)<a href="https://agentmods.dev/skills/tellahq/opensession/audit-codebase"><img src="https://agentmods.dev/badge/skills/tellahq/opensession/audit-codebase/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/tellahq/opensession/audit-codebase"><img src="https://agentmods.dev/badge/skills/tellahq/opensession/audit-codebase.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 | $0.00046 | $0.01703 |
| Opus 5.5 | $0.00018 | $0.00681 |
| Sonnet 5.5 | $0.00009 | $0.00341 |
| Haiku 4.5 | $0.00005 | $0.00170 |
Grade A, and why
audit-codebase 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit codebase
/audit-codebase → inventory every subsystem → bounded waves of read-only reviewers → validate each finding → audit the audit
You are the coordinator of a read-only audit. The question is not "are there bugs" and not "is this pretty". It is whether the codebase's data structures, state representation, control flow, algorithms and ownership boundaries could be materially simpler than they are.
Keep going until every subsystem has been reviewed and the finished audit has survived fresh checking passes. Adapted from Aaron Francis's audit prompt: https://gist.github.com/aarondfrancis/8735edbe48532f97ee5ea818db4dbd47
The read-only contract
Do not edit files, run tests, implement a recommendation, commit, or push.
Read-only inspection is the whole toolkit: reading files, grep and glob, git log, git diff, listing directories, reading CI config. The repository must be
byte-identical when you finish, working tree and index alike.
Everything you want changed goes into the report as a recommendation. Someone else decides whether to do it, and when.
If $ARGUMENTS names a scope (a directory, a package, a named subsystem), audit
that and record in the report that the boundary was narrowed deliberately.
Otherwise audit the whole repository.
Phase 0 — The report is the state
One canonical report accumulates everything and you update it as you go. Do not carry the inventory in your head: waves of workers will outlive your attention to any single row.
Write it outside the checkout, or you break the read-only contract:
- With Open Session's assets tools,
write_assettoaudit/report.md. That is session scratch space, not the repo, so it works in a read-only Ask session and shows up in the session's Assets tab. - Otherwise a file under
/tmp.
The report holds:
- Subsystem inventory (the coverage contract)
- Confirmed opportunities (validated findings, one row each)
- Explicit skips (a subsystem reviewed and found already clear)
- Cross-cutting patterns (the same shape in three places)
- Duplicates and superseded findings (what you merged, and into what)
- Final priorities and dependencies
- Audit log (which wave covered which rows, and when)
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 First seen · 169 lines · 46 tokens per session scan A 718a6658537b
audit-codebase is a skill published in the GitHub repository tellahq/opensession (399 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,703 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…