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 HiAgencia/hi-claude --skill auditgit clone --depth 1 https://github.com/HiAgencia/hi-claudeWrote 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/hiagencia/hi-claude/audit)<a href="https://agentmods.dev/skills/hiagencia/hi-claude/audit"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/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/hiagencia/hi-claude/audit"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/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 | $0.00118 | $0.00980 |
| Opus 5 | $0.00059 | $0.00490 |
| Sonnet 5 | $0.00024 | $0.00196 |
| Haiku 4.5 | $0.00012 | $0.00098 |
Grade A, and why
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 12d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hi-claude Audit
Orchestrate the hi-claude auditors, consolidate one actionable report, and apply only what the user approves.
Steps
- Parse target from
$ARGUMENTS:claude-md,memory,organization,roadmap,inventory,currency, orall(defaultall). - Launch the corresponding agents in parallel using the Agent tool (single message, multiple
calls):
hi-claude:claude-md-auditor,hi-claude:memory-auditor,hi-claude:organization-auditor,hi-claude:roadmap-auditor,hi-claude:inventory-auditor,hi-claude:currency-auditor. Pass each one the project root path and, for the memory auditor, the project's memory directory (~/.claude/projects/<slug>/memory/). - Consolidate their structured reports into ONE message in the user's language:
Report the measurement each auditor produced, never a letter: a grade is a verdict of value on the user's own project, and the rubrics already produce the datum.
## hi-claude Audit — <project>
📋 CLAUDE.md: <score/total> — <finding 1>, <finding 2>
🧠 Memory: <n checked, n with findings> — <finding 1>
🗺️ ROADMAP: <score/total> — <finding 1>
📁 Organization: <what was counted> — <finding 1>, <finding 2>
🧰 Inventory: <what was counted> — <finding 1>
🕰️ Currency: <n lines that expired of n> — <finding 1>, <finding 2>
Each finding: [evidence file:line] — what was observed — why it matters — proposed fix
- Respect the caps: max 1-2 findings per category in the main report (the agents already cap; do not re-expand). If an agent reported a 🚨 critical (secrets in plain text), surface it FIRST regardless of caps.
- Ask what to apply with AskUserQuestion: apply all / choose per item / nothing. NEVER apply without selection.
- Apply approved items only, one by one (the Guardian will confirm governed writes). For deletions of user files, show a summary of the file's content before deleting.
- Close with: "Want me to dig deeper into any category?" and, if it's been useful, remind that audits can run anytime.
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.
- 12d ago First seen · 63 lines · 118 tokens per session scan A b9d96b5e47e6
audit is a skill published in the GitHub repository HiAgencia/hi-claude (2 stars, last pushed 21d ago), licensed MIT. It adds 118 tokens to every session and 980 once invoked, about $0.0006 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…