rtk is a command-line proxy that filters and compresses output from development commands before it reaches an LLM's context. It is used with coding agents to reduce the tokens consumed by commands such as Git operations. The catalogue includes skills, commands, agents, and instructions for using rtk in agent workflows.
Borrowing it
Nothing to install: this file belongs to rtk-ai/rtk. 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/rtk-ai/rtk/develop/.claude/commands/tech/audit-codebase.mdgit clone --depth 1 https://github.com/rtk-ai/rtkWrote 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/rtk-ai/rtk/audit-codebase)<a href="https://agentmods.dev/commands/rtk-ai/rtk/audit-codebase"><img src="https://agentmods.dev/badge/commands/rtk-ai/rtk/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/commands/rtk-ai/rtk/audit-codebase"><img src="https://agentmods.dev/badge/commands/rtk-ai/rtk/audit-codebase.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 | $0.00016 | $0.02559 |
| Opus 5.5 | $0.00006 | $0.01024 |
| Sonnet 5.5 | $0.00003 | $0.00512 |
| Haiku 4.5 | $0.00002 | $0.00256 |
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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Codebase — Santé du Projet RTK
Score global et par catégorie (0-10) avec plan d'action priorisé.
Arguments
--category <cat>— Auditer une seule catégorie :secrets,security,deps,structure,tests,perf,ai--fix— Après l'audit, proposer les fixes prioritaires--json— Output JSON pour CI/CD
Usage
/tech:audit-codebase
/tech:audit-codebase --category security
/tech:audit-codebase --fix
/tech:audit-codebase --json
Arguments: $ARGUMENTS
Seuils de Scoring
| Score | Tier | Status |
|---|---|---|
| 0-4 | 🔴 Tier 1 | Critique |
| 5-7 | 🟡 Tier 2 | Amélioration requise |
| 8-10 | 🟢 Tier 3 | Production Ready |
Phase 1 : Audit Secrets (Poids: 2x)
# API keys hardcodées
Grep "sk-[a-zA-Z0-9]{20}" src/
Grep "Bearer [a-zA-Z0-9]" src/
# Credentials dans le code
Grep "password\s*=\s*\"" src/
Grep "token\s*=\s*\"[^$]" src/
# .env accidentellement commité
git ls-files | grep "\.env" | grep -v "\.env\.example"
# Chemins absolus hardcodés (home dir, etc.)
Grep "/home/[a-z]" src/
Grep "/Users/[A-Z]" src/
| Condition | Score |
|---|---|
| 0 secrets trouvés | 10/10 |
| Chemin absolu hardcodé | -1 par occ. |
| Credential réel exposé | 0/10 immédiat |
Phase 2 : Audit Sécurité (Poids: 2x)
Objectif : Pas d'injection shell, pas de panic en prod, error handling complet.
# unwrap() en production (hors tests)
Grep "\.unwrap()" src/ --glob "*.rs"
# Filtrer les tests : compter ceux hors #[cfg(test)]
# panic! en production
Grep "panic!" src/ --glob "*.rs"
# expect() sans message explicite
Grep '\.expect("")' src/
# format! dans des chemins injection-possibles
Grep "Command::new.*format!" src/
# ? sans .context()
# (approximation - chercher les ? seuls)
Grep "[^;]\?" src/ --glob "*.rs"
| Condition | Score |
|---|---|
| 0 unwrap() hors tests | 10/10 |
unwrap() en production |
-1.5 par fichier |
panic! hors tests |
-2 par occurrence |
? sans .context() |
-0.5 par 10 occ. |
| Injection shell potentielle | -3 par occurrence |
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 · 285 lines · 16 tokens per session scan A 277f9750b719
audit-codebase is a command published in the GitHub repository rtk-ai/rtk (84,655 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 2,559 once invoked, about $0.0001 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 commands, from other repositories
subagent-diagnose
Multi-agent failure-investigation orchestrator. Parallel to /subagent-implementation — same scratchpad + investigator + builder/surgeon + reviewer + FOLLOWUPS pattern — but starts from a failure, not a spec. Two modes share one loop: ci (failed CI run is the brief seed) and bug (freeform symptom paragraph is the brief…
quick-fix
Implement→review subagent loop with no planning phase, for a fix whose cause is known and whose shape is obvious, however many files it touches. No spec, no worktree, no docs or signals at the end; one audit. Routes to /subagent-diagnose on an unknown cause and to /atomic-plan on an open approach or contract choice.
optimize
Suggest concrete performance improvements for the given file or directory.
dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised with fixes, and kept improvements. Shadow-first; never auto-pushes. Runs on-demand or scheduled for off-hours.
debloat
Retroactive whole-repo bloat removal (spec H-2ii). Scores an existing repo on the deterministic bloat axes, writes BLOAT-REPORT.md, and — only behind a passing test-suite safety oracle — proposes gated refactor waves as a PR. The zero-risk adoption hook.
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.