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 skills/hknc/claude-evolve/setup-auditnpx skills add hknc/claude-evolve --skill setup-auditgit clone --depth 1 https://github.com/hknc/claude-evolveWrote 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/hknc/claude-evolve/setup-audit)<a href="https://agentmods.dev/skills/hknc/claude-evolve/setup-audit"><img src="https://agentmods.dev/badge/skills/hknc/claude-evolve/setup-audit.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 | $0.00095 | $0.00619 |
| Opus 5 | $0.00048 | $0.00309 |
| Sonnet 5 | $0.00019 | $0.00124 |
| Haiku 4.5 | $0.00010 | $0.00062 |
Grade A, and why
setup-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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Audit
Alias for /evolve audit. Audit and optimize Claude Code configuration.
Action
Invoke claude-evolve:evolve-setup-auditor agent via Task tool.
Execution
- Check prerequisite: Verify
$HOME/.claude-evolve/activeexists. If not, tell user to run/evolve initfirst and stop. - Determine mode from user request (see table below). Default is
full. - Spawn agent: Invoke
claude-evolve:evolve-setup-auditorvia Task tool with the mode parameter. - Report results to user.
Modes
| Mode | Trigger | What It Does |
|---|---|---|
full |
"audit my setup" (default) | Complete audit: security, coverage, learnings, recommendations |
quick |
"quick check", "fast audit" | Security + coverage check only |
security |
"is my setup secure" | Deep security analysis of settings and permissions |
optimize |
"optimize", "apply improvements" | Apply all improvements directly to toolkit |
consolidate |
"consolidate", "merge duplicates" | Merge similar components, remove redundancy |
migrate |
"migrate", "import from .claude" | Copy $HOME/.claude/ content to toolkit |
Error Handling
| Error | Action |
|---|---|
| No toolkit initialized | Tell user: "Run /evolve init first." |
| Agent finds no issues | Report: "Setup looks good. No issues found." |
| Agent can't read $HOME/.claude/ | Report what was accessible, note permission issues |
Expected Output
The agent produces a structured audit report with:
- Configuration summary (component counts by source)
- Security status (critical checks)
- Coverage analysis (gaps in agents/skills/rules)
- Recommendations (only actionable items)
- Migration availability (if $HOME/.claude/ has content not in toolkit)
Critical Rule
The agent reads from $HOME/.claude/ but never writes to it. All changes go to the toolkit at $HOME/.claude-evolve/toolkits/{name}/.
Relationship to /evolve audit
This skill is the natural-language entry point for the same functionality that /evolve audit provides via command routing. Both invoke the same evolve-setup-auditor agent.
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.
- 4d ago First seen · 56 lines · 95 tokens per session scan A c436e187c2e7
setup-audit is a skill published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 95 tokens to every session and 619 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…