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/codeverbojan/claude-code-kickstart/metricsgit clone --depth 1 https://github.com/codeverbojan/claude-code-kickstartWhat 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 | $0.00016 | $0.00421 |
| Opus 5 | $0.00008 | $0.00211 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
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 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.
What it actually says
Session Metrics
Read .claude/metrics.jsonl and show trends.
1. Read Data
Read .claude/metrics.jsonl. Each line is a JSON object with:
date,files_touched,verification_runs,gotchas_added,signals_captured,decisions_logged
If the file doesn't exist or is empty, report "No metrics yet. Run /wrap-up to start tracking session stats."
2. Show Summary
Display a table of the last 10 sessions:
Date Files Verified Gotchas Signals Decisions
2026-04-01 5 3 1 2 1
2026-04-02 8 4 0 0 2
...
3. Show Trends
If fewer than 5 sessions, show the table but skip trend analysis. Instead say: "Not enough data for trends yet (N sessions). Need at least 5."
With 5+ sessions, calculate and display:
- Average files per session (are sessions getting bigger or smaller?)
- Verification ratio (verification_runs / files_touched — are you verifying enough?)
- Signal trend (are signals decreasing over time? = fewer mistakes)
- Gotcha growth (total gotchas accumulated — the system's learned knowledge)
4. Insights
Based on the data, provide 1-2 actionable insights:
- If signals are increasing: "Mistake rate is rising. Consider running /retrospective."
- If verification ratio is low: "You're editing more than verifying. Run tests more often."
- If signals are decreasing: "Fewer mistakes over time — the gotchas are working."
- If no signals in last 5 sessions: "Clean streak — no mistakes detected in 5 sessions."
$ARGUMENTS
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 · 50 lines · 16 tokens per session scan A 46d88ffee946
metrics is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 421 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
plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
implement
Execute implementation by processing atomic task files one at a time with Context Pinning (Atomic Traceability Model).
cleanup
Detect and remove orphaned code, unused components, dead routes, and stale database artifacts.
_registry-protocol
This protocol is MANDATORY for ALL commands, agents, and phases.
taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
_subagent-discovery
Whenever a command needs to pick a subagent for a task (planning, task generation, or implementation execution). Do not hardcode agent names in command templates. Do not assume a specific agent exists.