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/test-routing.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/test-routing)<a href="https://agentmods.dev/commands/rtk-ai/rtk/test-routing"><img src="https://agentmods.dev/badge/commands/rtk-ai/rtk/test-routing/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/test-routing"><img src="https://agentmods.dev/badge/commands/rtk-ai/rtk/test-routing.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 | $0.00017 | $0.02223 |
| Opus 5.5 | $0.00007 | $0.00889 |
| Sonnet 5.5 | $0.00003 | $0.00445 |
| Haiku 4.5 | $0.00002 | $0.00222 |
Grade A, and why
test-routing 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 13d 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/test-routing
Vérifie le routing de commandes RTK sans exécution (dry-run). Utile pour tester si une commande a un filtre disponible avant de l'exécuter.
Usage
/test-routing <command> [args...]
Exemples
/test-routing git status
# Output: ✅ RTK filter available: git status → rtk git status
/test-routing npm install
# Output: ⚠️ No RTK filter, would execute raw: npm install
/test-routing cargo test
# Output: ✅ RTK filter available: cargo test → rtk cargo test
Quand utiliser
- Avant d'exécuter une commande: Vérifier si RTK a un filtre
- Debugging hook integration: Tester le command routing sans side-effects
- Documentation: Identifier quelles commandes RTK supporte
- Testing: Valider routing logic sans exécuter de vraies commandes
Implémentation
Option 1: Check RTK Help Output
COMMAND="$1"
shift
ARGS="$@"
# Check if RTK has subcommand for this command
if rtk --help | grep -E "^ $COMMAND" >/dev/null 2>&1; then
echo "✅ RTK filter available: $COMMAND $ARGS → rtk $COMMAND $ARGS"
echo ""
echo "Expected behavior:"
echo " - Command will be filtered through RTK"
echo " - Output condensed for token efficiency"
echo " - Exit code preserved from original command"
else
echo "⚠️ No RTK filter available, would execute raw: $COMMAND $ARGS"
echo ""
echo "Expected behavior:"
echo " - Command executed without RTK filtering"
echo " - Full command output (no token savings)"
echo " - Original command behavior unchanged"
fi
Option 2: Check RTK Source Code
COMMAND="$1"
shift
ARGS="$@"
# List of supported RTK commands (from src/main.rs)
RTK_COMMANDS=(
"git"
"grep"
"ls"
"read"
"err"
"test"
"log"
"json"
"lint"
"tsc"
"next"
"prettier"
"playwright"
"prisma"
"gh"
"vitest"
"pnpm"
"ruff"
"pytest"
"pip"
"go"
"golangci-lint"
"docker"
"cargo"
"smart"
"summary"
"diff"
"env"
"discover"
"gain"
"proxy"
)
# Check if command in supported list
if [[ " ${RTK_COMMANDS[@]} " =~ " ${COMMAND} " ]]; then
echo "✅ RTK filter available: $COMMAND $ARGS → rtk $COMMAND $ARGS"
echo ""
# Show filter details if available
case "$COMMAND" in
git)
echo "Filter: git operations (status, log, diff, etc.)"
echo "Token savings: 60-80% depending on subcommand"
;;
cargo)
echo "Filter: cargo build/test/clippy output"
echo "Token savings: 80-90% (failures only for tests)"
;;
gh)
echo "Filter: GitHub CLI (pr, issue, run)"
echo "Token savings: 26-87% depending on subcommand"
;;
pnpm)
echo "Filter: pnpm package manager"
echo "Token savings: 70-90% (dependency trees)"
;;
*)
echo "Filter: Available for $COMMAND"
echo "Token savings: >=20% (floor)"
;;
esac
else
echo "⚠️ No RTK filter available, would execute raw: $COMMAND $ARGS"
echo ""
echo "Note: You can still use 'rtk bypass $COMMAND $ARGS' to:"
echo " - Execute command without filtering"
echo " - Track usage in 'rtk gain --history'"
echo " - Measure potential for new filter development"
fi
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.
- 13d ago Changed 3572f6e2d6c0
- 1mo ago First seen · 363 lines · 17 tokens per session scan A 867700ae99f1
test-routing is a command published in the GitHub repository rtk-ai/rtk (84,655 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 2,223 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.