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 agentmods add commands/caspian-sun/claude-code-workflow/meta-auditgit clone --depth 1 https://github.com/Caspian-Sun/claude-code-workflowWrote 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/commands/caspian-sun/claude-code-workflow/meta-audit)<a href="https://agentmods.dev/commands/caspian-sun/claude-code-workflow/meta-audit"><img src="https://agentmods.dev/badge/commands/caspian-sun/claude-code-workflow/meta-audit.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00810 |
| Opus 5 | $0.00000 | $0.00405 |
| Sonnet 5 | $0.00000 | $0.00162 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
meta-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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are now the meta-audit coordinator. The user just typed /meta-audit. Your sole responsibility is to spawn a meta-auditor sub-agent to perform a full scan, then present the report's key findings to the user.
Command Arguments
The user may pass:
--focus=<dimension>— scan only one dimension (rule-violations/doc-drift/internal-consistency/traceability/dead-links/orphaned-assets)--output=<path>— override the default report location
No arguments = scan all 6 dimensions, write report to docs/retrospectives/<today's date>-meta-audit.md.
Execution Flow
1. Find the Previous Report (for trend comparison)
Glob(pattern="docs/retrospectives/*-meta-audit.md")
Sort by filename and take the most recent (excluding any same-day report that may already exist).
2. Spawn meta-auditor agent
Agent(
subagent_type="meta-auditor",
description="Engineering meta-audit",
prompt=<see prompt template below>
)
Prompt template (variables to fill are in <>):
Please execute a meta-audit and output the report to docs/retrospectives/<today>-meta-audit.md.
Scan dimensions: <full | focus=<dimension>>
Previous report (for trend comparison): <previousReportPath | first run>
Strict constraints:
- Only Read / Grep / Glob for scanning
- Only Write to the report path; do not touch any other files
- Do not reference git, do not modify .claude/, do not modify workspace/
Follow the execution steps and report format defined in .claude/agents/meta-auditor.md.
3. Receive summary and show to user
After receiving the summary returned by meta-auditor, output the following in the terminal:
## 📊 Meta-audit complete
**Report**: [docs/retrospectives/<date>-meta-audit.md](docs/retrospectives/<date>-meta-audit.md)
### Findings
- 🔴 Must fix: X items
- 🟡 Recommend fixing: Y items
- 🔵 Discussion: Z items
### Top 3 Must-Fix (prioritize these)
1. <1st item from agent>
2. <2nd item from agent>
3. <3rd item from agent>
### Trend (vs. last run)
- Resolved: A items ✅
- New: B items
- Persistently unaddressed: C items ⚠️
### Next Steps
Please review the full report. For accepted suggestions, follow the normal process to implement:
- Rule changes → edit .claude/rules/ directly
- Code changes → use /fix or normal development flow
- Discussion items → open a GitHub issue or discuss with the team
This command **does not auto-fix** — all changes require human decision.
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.
- 4d ago First seen · 98 lines · 0 tokens per session scan A 3748d5b6f8e3
meta-audit is a command published in the GitHub repository Caspian-Sun/claude-code-workflow (10 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 810 tokens. 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 commands, from other repositories
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
spark-prairie-fire
用星火燎原方法为从零起步的任务选择根据地和最小切入口。.
ship
Deliver the increment. Then go live with a rollback you have run.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
cost-tracker
Track session costs, understand token spend, and get optimization tips.
upgrade
Comprehensive dependency upgrade with security audit, prioritization, and validation.