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/koolamusic/claudefiles/rungit clone --depth 1 https://github.com/koolamusic/claudefilesWhat 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 | $0.00026 | $0.00437 |
| Opus 5 | $0.00013 | $0.00218 |
| Sonnet 5 | $0.00005 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
run 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 3d 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.
What it actually says
Execute one or more warden plans.
Parse the input
$ARGUMENTS is passed through to the runner unchanged. Supported forms:
- (empty): run every plan in phase order
<plan-id>(one or many): run only those plans by basename matchphase:<phase-name>: run all plans in one phase--strict: abort the suite on the first failing plan--destructive/--yes/--force: skip the destructive countdown- Any combination
Precondition: .warden/ must exist
if [ ! -f .warden/run.sh ]; then
echo "warden is not initialized in this project."
echo "Run /warden:design to bootstrap .warden/ from the plugin templates."
exit 1
fi
If the runner is missing, do not try to recover or fall back to copying templates. Surface the missing init to the user and stop.
Execute
bash .warden/run.sh $ARGUMENTS
Forward the runner's stdout and stderr unchanged. Capture the exit code.
Report the outcome
The runner writes its own summary banner. Do not duplicate it. After the runner exits:
- If exit 0: confirm green and point at the run summary (
.warden/runs/<id>.md). - If exit 1: state the suite failed; list the failing plans by reading the runner output. Suggest
/warden:triageto classify the failures and write remediation files. - If exit 2: a destructive suite refused to run non-interactively. Tell the user to re-run with
--destructiveif they meant it.
Do not analyse failures here; that is /warden:triage's job. The contract for this command is "execute and surface."
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.
- 3d ago First seen · 48 lines · 26 tokens per session scan A 8795ee3c4078
run is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 437 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
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
debug-playwright
Use this command to debug failing Playwright tests in a source-first, evidence-first workflow.
run-all-tests-and-fix
Execute the full test suite and systematically fix any failures, ensuring code quality and functionality. All test-related commands must pass before completion.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
fd-verify
Verify the implementation — run tests, check regression on affect.md files, review and scan; blocks /fd-done on failure.