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 skills add oliver-kriska/claude-elixir-phoenix --skill phx-auditgit 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/skills/oliver-kriska/claude-elixir-phoenix/phx-audit)<a href="https://agentmods.dev/skills/oliver-kriska/claude-elixir-phoenix/phx-audit"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/phx-audit/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/skills/oliver-kriska/claude-elixir-phoenix/phx-audit"><img src="https://agentmods.dev/badge/skills/oliver-kriska/claude-elixir-phoenix/phx-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00936 |
| Opus 5 | $0.00019 | $0.00468 |
| Sonnet 5 | $0.00008 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
phx-audit 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Health Audit
Comprehensive project-wide health assessment across five independent concern tracks.
Usage
phx-audit # Full audit (default)
phx-audit --quick # 2-3 minute pulse check
phx-audit --focus=security # Deep dive single area
phx-audit --focus=performance
phx-audit --since abc123 # Incremental audit since commit
phx-audit --since HEAD~10 # Audit last 10 commits
When to Use
- Quarterly health checks
- Before major releases
- After large refactors
- New team member onboarding (understand codebase health)
Iron Laws
- Complete every selected track before synthesizing — partial results make cross-category scores misleading
- Scope each track to concrete directories and checks — vague project-wide analysis produces generic findings
- Never compare scores across projects — track trends only within the same codebase
- Run quick mode before full mode — catch basic failures before expensive analysis
Portable Audit Workflow
- Create
.claude/audit/reports/and.claude/audit/summaries/. - Run the quick checks below. Stop and report a blocker when the project cannot compile or its test command cannot start.
- Complete five tracks: architecture, performance, security, tests, and dependencies. Native generic workers may run independent tracks in parallel when the runtime provides them; otherwise run every track sequentially in this session. Never require named custom agents.
- Write one evidence-focused report per track under
.claude/audit/reports/. Report issues only, cite paths and lines, and use one summary line for a clean area. - After all selected reports exist, deduplicate findings, identify
cross-category correlations, calculate scores using
references/scoring-methodology.md, and write.claude/audit/summaries/project-health-{date}.md.
If two or more optional workers fail or hit limits, finish the missing tracks sequentially. Never present an incomplete track as audited.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 109 lines · 38 tokens per session scan A 418ed5a7ce35
phx-audit is a skill published in the GitHub repository oliver-kriska/claude-elixir-phoenix (542 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 936 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 2026-09-03.
Other skills, from other repositories
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
bug-investigate
Use when someone wants to know WHY something is broken and has not asked for it to be fixed — "why is this happening", "what's causing this error", "find out what's wrong", "diagnose this before we decide". Also use before committing to a fix, when the cause is unknown and the decision depends on it. Not for fixing …
gurobi-advanced-features
When the user wants to use Gurobi beyond plain model building — callbacks for lazy constraints, user cuts, heuristic solution injection, and early termination; IIS computation for diagnosing an infeasible model; the solution pool; the multi-objective API; the matrix API (addMVar/addMConstr); MIP starts; and parameter…
cige-product-defect-escalation
Invoked by cige-failure-classification when a run is classified as a Product Defect: execution reached the system under test, the environment is healthy, execution steps are current — but the outcome does not match Intent.
cige-stale-execution-repair
Invoked by cige-failure-classification in two situations: Outdated Test Logic (Mode A — repair Execution[]) and a confirmed False Positive (Mode B — strengthen Guardrails). These are different repairs with different targets; do not conflate them.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.