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 David405/harness-kit --skill code-auditgit clone --depth 1 https://github.com/David405/harness-kitWrote 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/david405/harness-kit/code-audit)<a href="https://agentmods.dev/skills/david405/harness-kit/code-audit"><img src="https://agentmods.dev/badge/skills/david405/harness-kit/code-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/david405/harness-kit/code-audit"><img src="https://agentmods.dev/badge/skills/david405/harness-kit/code-audit.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 | $0.00081 | $0.00436 |
| Opus 5.5 | $0.00032 | $0.00174 |
| Sonnet 5.5 | $0.00016 | $0.00087 |
| Haiku 4.5 | $0.00008 | $0.00044 |
Grade A, and why
code-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 2mo 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.
What it actually says
Code audit
Kit-owned. Edit in the harness-kit repo, not in the consumer repo.
Periodic, never per sprint. The gate asks "can this diff ship?"; this asks "where should we invest refactoring effort, and what is safe to touch?"
When to use
Milestone, quarter, pre-hardening, pre-handover, or before a large refactor.
When not to use
Per-contract checking → code-quality-gate. Security review of contracts → solidity-audit.
The absolute constraint
Refactor implementation, not behaviour. Every recommendation preserves externally observable behaviour. Where cleanliness and behavioural safety conflict, safety wins. Equivalence is proven, not asserted: characterization tests must pass against the code as it stands today, then pass unchanged after the refactor.
Any uncertainty downgrades a finding to "Potential improvement — requires behavioural verification".
Rules that matter
- Declare scope and the audited commit or tag. Findings without a ref are unactionable.
- Work all 15 taxonomy categories; record "no material findings" rather than omitting one.
- Validate before reporting — call sites, consumers, tests, framework registration.
- Materiality test: unconventional but clear, safe, locally appropriate code is not a finding.
- Suspected functional bugs are reported, never fixed inside the audit.
- The audit proposes a
FEATURES.jsonseed; a human accepts findings into the ledger.
Forms
templates/CODE_AUDIT_CONTRACT.md · templates/CODE_AUDIT_FINDING.md
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.
- 2mo ago First seen · 47 lines · 81 tokens per session scan A 345eaeae340b
code-audit is a skill published in the GitHub repository David405/harness-kit (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 436 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
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"…
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…
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…