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 joris887/exosuit --skill doctorgit clone --depth 1 https://github.com/joris887/exosuitWrote 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/joris887/exosuit/doctor)<a href="https://agentmods.dev/skills/joris887/exosuit/doctor"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/doctor/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/joris887/exosuit/doctor"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/doctor.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 | $0.00023 | $0.02514 |
| Opus 5 | $0.00012 | $0.01257 |
| Sonnet 5 | $0.00005 | $0.00503 |
| Haiku 4.5 | $0.00002 | $0.00251 |
Grade B, and why
doctor 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 9d 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.
echo "Project profile: $(cat .claude/hooks/state/project-profile 2>/dev/null || echo 'standard (default)')" How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
doctor
Run a comprehensive health check on the framework configuration and project setup.
1. Command Verification
Read CLAUDE.md Commands section. For each configured command (test, lint, format, build, typecheck):
2. Hook Dependencies
For each hook in .claude/settings.json:
- Verify the hook script file exists and is executable
- For
post-edit-format.sh: check if at least one formatter is installed (prettier, biome, ruff, black, rustfmt, gofmt) - For shell hook scripts: verify git is available (used by stop.sh, session-start.sh)
- Optional: check if jq is available (hooks fall back to sed without it)
Report: PASS/WARN (missing optional tools)/FAIL (missing required tools)
3. Rule Relevance
For each rule in .claude/rules/:
- Read the YAML frontmatter
paths:field - Check if any files in the project match those patterns
- Report: ACTIVE (matches found) / DORMANT (no matches — rule will never trigger)
- Check
docs/sessions/.activity-log.jsonlfor rule trigger frequency over the last 5 sessions - Rules that are ACTIVE but have zero trigger events in 5+ sessions: report as REVIEW (candidate for retirement)
- The "pull their weight" test: if a rule never changes AI behavior, it wastes context budget
4. Skill Dependencies & Cross-References
For each skill with depends-on: in YAML frontmatter:
- Verify each dependency skill exists in
.claude/skills/ - For skills with
requires:— check binaries, commands, and files - Report: PASS/WARN (optional dependency missing)/FAIL (required dependency missing)
For each skill with calls: in skills-registry.json:
What ships with it
1 file 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.
- 9d ago First seen · 238 lines · 23 tokens per session scan B f864d376d0b6
doctor is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 20d ago), licensed MIT. It adds 23 tokens to every session and 2,514 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
investigate
Systematic root-cause debugging: find the cause before writing any fix.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.
optimize
Analyze and suggest performance improvements for code, queries, or systems.
code-review
Review code changes for concrete defects.