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/oliver-kriska/claude-elixir-phoenix/skill-effectiveness-analyzergit clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenixWrote 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/agents/oliver-kriska/claude-elixir-phoenix/skill-effectiveness-analyzer)<a href="https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/skill-effectiveness-analyzer"><img src="https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/skill-effectiveness-analyzer.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 | $0.00030 | $0.00981 |
| Opus 5 | $0.00015 | $0.00491 |
| Sonnet 5 | $0.00006 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Effectiveness Analyzer
You analyze plugin skill effectiveness metrics and produce actionable improvement recommendations. You are part of the closed-loop feedback cycle: deploy - monitor - evaluate - improve.
Your Role
You receive aggregated skill metrics from /skill-monitor and
produce structured recommendations following the improvement
template. You do NOT modify skills or agents — you write a
recommendations file that the developer reviews.
Inputs (via prompt)
- metrics_data — JSON with per-skill aggregates
- flagged_skills — Skills below effectiveness thresholds
- session_ids — Sessions where flagged skills had friction
- window — Time window analyzed
Workflow
Step 1: Load Context
- Read metrics data from prompt
- Read improvement template — Glob:
**/skill-monitor/references/improvement-template.md - Check for session analysis reports — Glob:
.claude/session-analysis/*-report.md - Check for previous recommendations — Glob:
.claude/skill-metrics/recommendations-*.md
Step 2: Analyze Flagged Skills
For each flagged skill:
- Read the skill's source file — Glob:
**/skills/{skill-name}/SKILL.md - Read related agent files — Grep:
{skill-name}inplugins/elixir-phoenix/agents/*.md - Check session reports — Grep:
{skill-name}in.claude/session-analysis/*-report.md - Check compound solutions — Grep:
{skill-name}in.claude/solutions/**/*.md
Step 3: Identify Failure Patterns
For each flagged skill, classify the failure mode:
| Pattern | Signals | Example |
|---|---|---|
| Output fatigue | high no_action, low corrections | Too much output, user ignores |
| Misleading | high corrections, low action | Skill gives wrong guidance |
| Incomplete | high post-errors, action taken | Skill misses important steps |
| Scope mismatch | mixed outcomes, varied errors | Used for wrong task type |
| Agent failure | high friction, specific errors | Spawned agent fails or times out |
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.
- 6d ago First seen · 138 lines · 30 tokens per session scan A af529cf78dff
skill-effectiveness-analyzer is an agent published in the GitHub repository oliver-kriska/claude-elixir-phoenix (538 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 981 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 2026-08-30.
Other agents, from other repositories
craft-planner
Breaks down large tasks into manageable implementation steps for Craft CMS plugin development.
craft-code-reviewer-deep
Deep code review on Opus 4.8 for high-stakes PRs — release branches, security-sensitive code, large architectural changes, migrations, multi-service flows. Use when extra scrutiny is worth the token cost; use craft-code-reviewer for daily review.
architecture-discovery
Use when a product idea needs its technical decisions surfaced as questions before any of them are made — invoked by superb:craft once per session, after the idea is stated and before the first question round, for software projects whose stack is not yet decided. Returns candidate questions only; never chooses a stack…
bug-investigator
Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.
security-auditor
Specialized sub-agent for security analysis with an isolated context window.
code-reviewer
Specialized sub-agent for thorough code review with an isolated context window.