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/reportgit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/koolamusic/claudefiles/report)<a href="https://agentmods.dev/commands/koolamusic/claudefiles/report"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/report.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 | $0.00040 | $0.00861 |
| Opus 5 | $0.00020 | $0.00430 |
| Sonnet 5 | $0.00008 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
report 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a stakeholder summary for a warden run. Tone is WhatsApp-casual: short, plain, lead with user-impact. No changelog dump. No filler. Own any regressions plainly.
Parse the input
$ARGUMENTS:
- Empty: most recent run.
<run-id>: specific run.
Read the run
if [ -n "$ARGUMENTS" ]; then
RUN_ID="$ARGUMENTS"
else
RUN_ID=$(ls -1 .warden/runs/*.md 2>/dev/null | sed -E 's|.*/||; s|\.md$||' | sort -r | head -1)
fi
Read .warden/runs/${RUN_ID}.md for the per-plan results.
Pull trend context from JSONL
If .warden/runs/asserts.jsonl exists, derive:
-
Regressions in this run: assertions that failed here but passed in the prior run:
PREV_RUN=$(jq -r ".run" .warden/runs/asserts.jsonl | sort -u | grep -v "$RUN_ID" | tail -1) jq -c "select(.run == \"$RUN_ID\" and .status == \"fail\") | .name" .warden/runs/asserts.jsonl > /tmp/now-fail jq -c "select(.run == \"$PREV_RUN\" and .status == \"pass\") | .name" .warden/runs/asserts.jsonl > /tmp/prev-pass grep -Fxf /tmp/prev-pass /tmp/now-fail # regressions -
Newly green: assertions that failed in the prior run and pass now.
-
Streaks: how many consecutive runs the suite has been green or red overall.
If only one run exists, skip trends and report only this run.
Pull observations
If .warden/runs/observations.jsonl exists, mention any standout measurement that changed materially from the prior run (e.g. boot time tripled). Only include if non-trivial.
Write the report
Path: .warden/runs/${RUN_ID}-report.md.
Structure (use only the sections that have content; do not pad):
# Run report: ${RUN_ID}
**Status**: green | partial (N failures) | red (M failures)
## What shipped
- One-line takeaways of what's working now that wasn't, if any.
## What regressed
- For each regression: which area, what broke, the assertion id and a half-sentence on impact.
- If zero regressions: skip this section entirely.
## What's still red
- Open failures grouped by phase, one line each.
- Link to .warden/remediation/<file>.md if triage has produced one.
## Trend
- Streak ("green for 4 runs" / "first red after 6 green").
- Any observation worth flagging (boot times, queue depth).
- Skip if there's no signal.
## Next
- One sentence on the recommended next action.
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 · 93 lines · 40 tokens per session scan A d3a78326bc5a
report is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 861 once invoked, about $0.0002 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.