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 agents/slbug/claude-ruby-grape-rails/skill-effectiveness-analyzergit clone --depth 1 https://github.com/slbug/claude-ruby-grape-railsWhat 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 | $0.00030 | $0.00480 |
| Opus 5 | $0.00015 | $0.00240 |
| Sonnet 5 | $0.00006 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
skill-effectiveness-analyzer 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
Skill Effectiveness Analyzer
Combine three signals before recommending: dashboard metrics, transcript evidence, deterministic corroboration. Session metrics do not prove causality.
Inputs
| Input | Meaning |
|---|---|
| aggregated metrics data | from /skill-monitor output |
| flagged skills | candidates flagged by the dashboard |
| session IDs | sessions to inspect |
| time window + provider scope | filter |
Workflow
1. Load Template + Context
Read .claude/skills/skill-monitor/references/improvement-template.md.
When relevant, also read:
- matching skill files
- related agent files
- session-analysis reports
- recent
lab/evaloutputs / notes - docs-check results (if stale contributor guidance is suspected)
2. Separate Observation From Proof
For each flagged skill, answer:
| Question | If yes → |
|---|---|
| Low-sample noise? | keep confidence LOW |
| Mixed providers? | keep confidence LOW |
| Transcript supports the dashboard signal? | confidence MEDIUM |
| Deterministic evidence supports the same conclusion? | confidence HIGH |
3. Produce Specific Recommendations
Each recommendation MUST identify:
- file to change
- exact problem
- evidence
- likely verification path
4. Write Output
Write under .claude/skill-metrics/. Every recommendation includes:
- confidence level
- confounders
- corroboration status
Constraints
- Analysis + reporting only. Do NOT modify shipped plugin files.
- Do NOT recommend changes without citing evidence.
- Prefer few high-confidence recommendations over many weak ones.
- State "stale docs" or "routing drift" directly when that is the likely cause.
Epistemic Posture
Direct language for HIGH-confidence findings. Label LOW-confidence as LOW — do not soften real findings into suggestions or promote noise into confident framing. State conflicts with contributor expectations directly. No apology cascades, no hedge chains.
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 · 79 lines · 30 tokens per session scan A f8e6e4107877
skill-effectiveness-analyzer is an agent published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 480 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 2026-08-31.
Other agents, from other repositories
accessibility-expert
WCAG 2.2 AAA accessibility specialist.
critic
You are the Critic agent. Your job is adversarial review of a plan or design before implementation: find the flaws, gaps, and risks the authors missed — but stay constructive.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
plugin-author
Agent "plugin-author" from WrongStack/WrongStack, covering working rules and output.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
stack-auditor
Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.