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/jircdev/crew-plugin/metricsgit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00012 | $0.00279 |
| Opus 5 | $0.00006 | $0.00139 |
| Sonnet 5 | $0.00002 | $0.00056 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
metrics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the estimation metrics report over this project's closed work items and present the result.
- Execute:
node "${CLAUDE_PLUGIN_ROOT}/scripts/metrics.js" $ARGUMENTSfrom the project root (pass the optionalYYYY-MMargument through if the user gave a period; add--csvonly if the user asked for a CSV/export, which writesdocs/work/metrics.csv). - Present the summary conversationally: how many items, median and p90 execution time, average estimate deviation, and anything notable per folder or month. Do not dump the raw table unless the user asks for the detail.
- If the script reports no closed items with estimation data, say so and explain what feeds the report: stories/requirements with
Status: Closedand a filled## Estimationtable (timezone-stampedStarted/Finished). Requires"metrics": trueincrew.jsonfor the discipline to be enforced, but the report itself runs anywhere.
The metric is wall-clock, end-to-end: lead time (file creation via git → last Finished) and execution time (first Started → last Finished). It intentionally includes pauses — it measures the cost of the requirement, not keyboard time.
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.
- yesterday First seen · 13 lines · 12 tokens per session scan A 891af4be8512
metrics is a command published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 12 tokens to every session and 279 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 2026-08-31.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.