Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Salmonellasarduri/claude-skill-analyticsnpx agentmods add commands/salmonellasarduri/claude-skill-analytics/reportWrote 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/salmonellasarduri/claude-skill-analytics/report)<a href="https://agentmods.dev/commands/salmonellasarduri/claude-skill-analytics/report"><img src="https://agentmods.dev/badge/commands/salmonellasarduri/claude-skill-analytics/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 5.1 | $0.00012 | $0.00268 |
| Opus 5 | $0.00006 | $0.00134 |
| Sonnet 5 | $0.00002 | $0.00054 |
| Haiku 4.5 | $0.00001 | $0.00027 |
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 7d 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
Skill Usage Report
Run the analytics script
PYTHONIOENCODING=utf-8 python3 scripts/skill_analytics.py --update-ts
Options:
--days 7— last 7 days only--days 30— last 30 days only--skill codex-analyst— filter to a specific skill--format json— output as JSON (for automation)
If python3 is not available, try python instead.
Present the results
Show the script output and highlight:
- Signals & Recommendations: DORMANT / INVESTIGATE items need attention
- Top skills: Which skills are driving the most value
- Uncategorized: New skills that could benefit from category assignment
Optional: Improvement actions
If asked to improve a low-usage skill:
- Read the skill's SKILL.md
- Compare with usage data
- Suggest Trigger Conditions improvements
- Edit SKILL.md after user approval
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.
- 7d ago First seen · 37 lines · 12 tokens per session scan A 82fb585e7c07
report is a command published in the GitHub repository Salmonellasarduri/claude-skill-analytics (1 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 268 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
repo-cleanup
Commit accumulated spec doc changes: survey, group by logical batch, branch, commit, merge.
triage_stale.spec
Task: t-1355 Command: brana backlog triage-stale.
session.spec
Task: t-1343 Related: tasks.spec.md (rotation contract).
reference.spec
Task: t-1341 Related: docs/architecture/testing-validation.md (canonical enum source).
init
An initialization command for the prompt-vault logging environment. It sets up the files and preferences needed to record coding-agent sessions.
log
A command definition for recording completed work as a phase log, including the user request, actions, results, decisions and next steps.