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 pincerhq/pincer --skill doctor-troubleshootinggit clone --depth 1 https://github.com/pincerhq/pincerWrote 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/pincerhq/pincer/doctor-troubleshooting)<a href="https://agentmods.dev/skills/pincerhq/pincer/doctor-troubleshooting"><img src="https://agentmods.dev/badge/skills/pincerhq/pincer/doctor-troubleshooting/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/pincerhq/pincer/doctor-troubleshooting"><img src="https://agentmods.dev/badge/skills/pincerhq/pincer/doctor-troubleshooting.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 | $0.00051 | $0.00472 |
| Opus 5.5 | $0.00020 | $0.00189 |
| Sonnet 5.5 | $0.00010 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
Doctor troubleshooting 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 2mo 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
Doctor troubleshooting
pincer doctor runs 25+ security and configuration checks and prints a
traffic-light report with an overall score out of 100.
pincer doctor # human-readable table
pincer doctor --json # machine-readable, for scripting
Reading the report
Each check has:
- A status icon: ✅ pass, ⚠️ warning, ❌ critical, ➖ skipped (not applicable to this deployment).
- A category (grouped in the table, e.g. filesystem permissions, secrets, network exposure).
- A message describing what was found.
- A fix hint — a concrete, actionable next step, not just a description of the problem.
When helping a user interpret a report, prioritize critical findings first, then warnings. Skipped checks are not failures — they mean the check doesn't apply (e.g. a check for a feature the user has disabled).
Common categories
- Filesystem permissions: directories like the skills root or data dir
having overly permissive bits (e.g. not
755). - Secrets: API keys or tokens present in config that should be in environment variables, or vice versa.
- Network exposure: services bound to
0.0.0.0when they should be local-only, missing auth on exposed endpoints.
Workflow
- Run
pincer doctor(or--jsonif you need to parse it programmatically). - Walk through critical findings first — each has a fix hint; apply it or walk the user through applying it.
- Re-run
pincer doctorafter changes to confirm the score improved and the specific check now passes. - Don't just report the score — explain what a low score on a specific check actually means for the user's setup, since a 100/100 score isn't itself the goal, an appropriately secured deployment is.
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.
- 2mo ago First seen · 51 lines · 51 tokens per session scan A 3ca088181b50
Doctor troubleshooting is a skill published in the GitHub repository pincerhq/pincer (44 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 472 once invoked, about $0.0002 per session on Opus 5.5. 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.
Doctor troubleshooting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Doctor troubleshootingpincerhq/pincer | Skill | 44 | yesterday | MIT | A | 51 | Claude Code, Codex |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |