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.
git clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/samibs/skillfoundry/metrics)<a href="https://agentmods.dev/commands/samibs/skillfoundry/metrics"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/metrics/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/samibs/skillfoundry/metrics"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/metrics.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.04503 |
| Opus 5.5 | $0.00000 | $0.01801 |
| Sonnet 5.5 | $0.00000 | $0.00901 |
| Haiku 4.5 | $0.00000 | $0.00450 |
Grade B, and why
metrics scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
SUCCESS_RATE=$(cat .claude/metrics.json | jq '.summary.success_rate') How it starts
The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metrics Dashboard
View and analyze execution metrics for the Claude AS framework.
OPERATING MODE
/metrics → Show metrics dashboard
/metrics agents → Agent performance breakdown
/metrics stories → Story completion analysis
/metrics errors → Error analysis and patterns
/metrics trends → Trend analysis over time
/metrics export [format] → Export metrics (json/csv/md)
/metrics reset → Reset metrics (with confirmation)
DASHBOARD VIEW
On /metrics invocation, display the comprehensive dashboard:
METRICS DASHBOARD
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
PROJECT: [project-name]
PERIOD: All time (since [start-date])
QUICK STATS
┌────────────────────────────────────────────────────────────────┐
│ Executions: [N] │ Success: [X]% │ Stories: [N] │ Tokens: [X]K │
└────────────────────────────────────────────────────────────────┘
RECENT ACTIVITY (Last 7 days)
├── Executions: [N]
├── Stories Completed: [N]
├── Success Rate: [X]%
└── Avg Tokens/Execution: [X]K
TOP PERFORMING AGENTS
1. [agent-name]: [X]% success ([N] calls)
2. [agent-name]: [X]% success ([N] calls)
3. [agent-name]: [X]% success ([N] calls)
ATTENTION NEEDED
[List any metrics below threshold]
Use /metrics [category] for detailed breakdowns.
AGENT METRICS
On /metrics agents:
AGENT PERFORMANCE METRICS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
OVERVIEW
┌──────────────────┬──────────┬──────────┬──────────┬──────────┬──────────┐
│ Agent │ Calls │ Success │ Partial │ Failed │ Avg Tok │
├──────────────────┼──────────┼──────────┼──────────┼──────────┼──────────┤
│ ruthless-coder │ [N] │ [X]% │ [X]% │ [X]% │ [X]K │
│ ruthless-tester │ [N] │ [X]% │ [X]% │ [X]% │ [X]K │
│ gate-keeper │ [N] │ [X]% │ [X]% │ [X]% │ [X]K │
│ cold-architect │ [N] │ [X]% │ [X]% │ [X]% │ [X]K │
│ docs-codifier │ [N] │ [X]% │ [X]% │ [X]% │ [X]K │
│ debug-hunter │ [N] │ [X]% │ [X]% │ [X]% │ [X]K │
└──────────────────┴──────────┴──────────┴──────────┴──────────┴──────────┘
PERFORMANCE RANKING
1. 🥇 [agent]: [X]% success rate
2. 🥈 [agent]: [X]% success rate
3. 🥉 [agent]: [X]% success rate
TOKEN EFFICIENCY
Most Efficient: [agent] ([X] tokens/call avg)
Least Efficient: [agent] ([X] tokens/call avg)
RECENT FAILURES BY AGENT
┌──────────────────┬──────────┬────────────────────────────────────┐
│ Agent │ Failures │ Common Cause │
├──────────────────┼──────────┼────────────────────────────────────┤
│ [agent] │ [N] │ [most common error type] │
└──────────────────┴──────────┴────────────────────────────────────┘
RECOMMENDATIONS
[Based on agent performance, suggest improvements]
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.
- 1mo ago First seen · 534 lines · 0 tokens per session scan B f5e7a3aebe2e
metrics is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,503 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
act
Execute the implementation plan with TDD.
tailtest
Generate or update tests for $ARGUMENTS.
sessions
Generate implementation session prompts from a PRD or research doc.
deploy
Command "deploy" from PraveenJayaprakash-JP/repomemory, covering deployment workflow, 1. pre-deploy checks, 2. build verification, 3. environment validation and 4. deployment steps (platform detection).
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.