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/rtk-ai/rtk/codereviewgit clone --depth 1 https://github.com/rtk-ai/rtkWhat 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 | $0.00014 | $0.02252 |
| Opus 5 | $0.00007 | $0.01126 |
| Sonnet 5 | $0.00003 | $0.00450 |
| Haiku 4.5 | $0.00001 | $0.00225 |
Grade A, and why
codereview 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 2d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RTK Code Review
Review locale de la branche courante avant création de PR. Applique les critères de qualité RTK.
Principe: Preview local → corriger → puis créer PR propre.
Usage
/tech:codereview # 🔴 + 🟡 uniquement (compact)
/tech:codereview --verbose # + points positifs + 🟢 détaillées
/tech:codereview main # Review vs main (défaut: master)
/tech:codereview --staged # Seulement fichiers staged
/tech:codereview --auto # Review + fix loop
/tech:codereview --auto --max 5
Arguments: $ARGUMENTS
Étape 1: Récupérer le contexte
# Parse arguments
VERBOSE=false
AUTO_MODE=false
MAX_ITERATIONS=3
STAGED=false
BASE_BRANCH="master"
set -- "$ARGUMENTS"
while [[ $# -gt 0 ]]; do
case "$1" in
--verbose) VERBOSE=true; shift ;;
--auto) AUTO_MODE=true; shift ;;
--max) MAX_ITERATIONS="$2"; shift 2 ;;
--staged) STAGED=true; shift ;;
*) BASE_BRANCH="$1"; shift ;;
esac
done
# Fichiers modifiés
git diff "$BASE_BRANCH"...HEAD --name-only
# Diff complet
git diff "$BASE_BRANCH"...HEAD
# Stats
git diff "$BASE_BRANCH"...HEAD --stat
Étape 2: Charger les guides pertinents (CONDITIONNEL)
| Si le diff contient... | Vérifier |
|---|---|
src/**/*.rs |
CLAUDE.md sections Error Handling + Tests |
src/core/filter.rs ou src/cmds/**/*_cmd.rs |
Filter Development Checklist (CLAUDE.md) |
src/main.rs |
Command routing + Commands enum |
src/core/tracking.rs |
SQLite patterns + DB path config |
src/core/config.rs |
Configuration system |
src/hooks/init.rs |
Init patterns + hook installation |
.github/workflows/ |
CI/CD multi-platform build targets |
tests/ ou fixtures/ |
Testing Strategy (CLAUDE.md) |
Cargo.toml |
Dependencies + build optimizations |
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.
- 2d ago First seen · 261 lines · 14 tokens per session scan A 297e3bd3e33d
codereview is a command published in the GitHub repository rtk-ai/rtk (78,131 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 2,252 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
boldguy-linkedin-answer
Draft a LinkedIn comment on a post, referencing the guide's relevant section, in Flow style with AI markers removed.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
worktree
Create a git worktree for isolated feature/fix work.
sync
Check guide/landing synchronization status.
version
Display current guide and Claude Code versions.