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 Borda/AI-Rig --skill rig-doctorgit clone --depth 1 https://github.com/Borda/AI-RigWrote 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/borda/ai-rig/rig-doctor)<a href="https://agentmods.dev/skills/borda/ai-rig/rig-doctor"><img src="https://agentmods.dev/badge/skills/borda/ai-rig/rig-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/borda/ai-rig/rig-doctor"><img src="https://agentmods.dev/badge/skills/borda/ai-rig/rig-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 | $0.00016 | $0.00369 |
| Opus 5.5 | $0.00006 | $0.00148 |
| Sonnet 5.5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
Rig Doctor 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 today.
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
Rig Doctor
Run rig_doctor and interpret the report. Doctor is read-only.
Checks
- Plugin is loaded and reports the expected version.
package.json,rig.json,src/version.ts, and the README marker agree.- Agent files are installed and stamped with the current version.
- Git is available and a local Git grant state can be read.
- The artifact root exists or can be created, and is gitignored.
- Configured gates are detectable.
- Stale run directories older than the configured TTL are reported.
Use action: "assets" (CLI: opencode-rig doctor --assets) to curate the shipped cards: rig.json roster agreement, skill frontmatter and headings, relative reference links, duplicated prose, and oversized skill or role cards. Roster drift and dead links fail; duplication and size warn.
Response
Report each line as pass, warn, or fail. For every failure, give the exact command or edit that fixes it:
- Missing or stale agents:
opencode-rig init --project(or--upgrade). - Missing Git grant: answer Approve always once in the main checkout, or keep per-commit questions.
- Missing artifact ignore: add
.opencode-rig/to.gitignore. - No gates: configure a Makefile or package script, or set
options.gates. - Asset roster drift: update
rig.jsonandsrc/resources/agents.jsontogether with the card. - Dead reference link or duplicated prose: fix the link, or move the shared text into a reference file.
Do not change files while diagnosing. Do not run paid checks.
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.
- today First seen · 34 lines · 16 tokens per session scan A 7ce23325af18
Rig Doctor is a skill published in the GitHub repository Borda/AI-Rig (29 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 369 once invoked, about $0.0001 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 2026-10-28.
Other skills, from other repositories
anomaly-alert
Identify anomalous sessions using Agent Monitor data — cost outliers from the pricing engine, token anomalies (cache miss spikes, compaction baseline surges), unusual event type ratios (PreToolUse/PostToolUse gaps, APIError clusters), behavioral deviations from workflow intelligence (complexity score outliers, error…
transcript-grep
Search a Claude Code session transcript for a string or regex pattern and show every matching message with surrounding context. Reads /api/sessions/:id/transcript and resolves sessions via /api/sessions?limit= from the Agent Monitor dashboard. Use when hunting for a specific message, prompt, tool call, or error inside…
hook-inventory
Inventory hooks across the user, project, and project-local settings plus the /.claude/hooks scripts directory — read through the Agent Monitor Config Explorer API — and flag hooks that POST to the network or run arbitrary commands. Reads /api/cc-config/hooks and /api/cc-config/hook-scripts. Use when auditing hook…
regression-watch
Detect quality and efficiency regressions over time using Agent Monitor data — rising error rate (APIError events), falling cache hit rate, growing compaction frequency, and climbing cost-per-session. Splits history into an earlier baseline window and a recent window and reports which metrics are getting worse, by how…
hook-failure-audit
Audit hook delivery health from Agent Monitor data — balance PreToolUse vs PostToolUse (a gap means tools that started but never reported back), detect missing Stop/SubagentStop terminators (sessions/subagents that never closed), and check for stale ingestion (no recent events). Use when hooks look unreliable or…
event-trace
Trace the full event chain for one Claude Code session into an ordered timeline of every event type with toolname and summary, highlighting gaps, out-of-order events, and failures. Reads /api/events?sessionid= and /api/sessions/:id from the Agent Monitor dashboard. Use when debugging what a session actually did, step…