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/agent-rig/rig/rig-doctornpx skills add agent-rig/rig --skill rig-doctorgit clone --depth 1 https://github.com/agent-rig/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/agent-rig/rig/rig-doctor)<a href="https://agentmods.dev/skills/agent-rig/rig/rig-doctor"><img src="https://agentmods.dev/badge/skills/agent-rig/rig/rig-doctor.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 | $0.00105 | $0.01403 |
| Opus 5 | $0.00053 | $0.00701 |
| Sonnet 5 | $0.00021 | $0.00281 |
| Haiku 4.5 | $0.00011 | $0.00140 |
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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rig-doctor — is this project set up for rig?
Inspect the environment, the tracker/board, the repo's gates, and .rig/config.json,
then report what would make rig run worse or fail — each finding with the exact
fix. Read-only by default. With --fix, apply the safe fixes after showing
them and getting a yes; leave sensitive changes (auth, branch protection) as
printed commands.
Pairs with /rig-onboard: onboard installs, doctor verifies.
Output
Group findings by severity and print the fix under each:
rig-doctor — <project> on <branch>
BLOCKERS (n) … rig won't work right until these are fixed
WARNINGS (n) … rig runs, but ungated or degraded
NITS (n) … advisories
✓ when a section is clean.
Read .rig/config.json first (if absent → the only blocker is "not onboarded;
run /rig-onboard"). Everything below is gated on what the config actually uses
(e.g. skip board checks when tracker.provider ≠ github or no tracker.board).
Checks
Blockers
- gh present + authed —
gh --version,gh auth status. Fix: install https://cli.github.com /gh auth login. (manual — interactive) projectscope — whentracker.boardis set,gh auth statusmust listproject. Fix:gh auth refresh -s project --hostname github.com. (manual)- board reachable —
gh project view <n> --owner <owner>succeeds, and the adapter returns: run the resolved tracker adapter'sselect --limit 1(.rig/rig-trackerif executable, else<RIG_DIR>/scripts/rig-tracker.sh). Fix: correcttracker.board.owner/projectNumber. - config valid —
.rig/config.jsonparses and matchesrig.schema.json(.rig/schema.json).vcs.baseRefandvcs.defaultBranchexist on the remote (git ls-remote --heads origin <branch>). Fix: correct the fields. - test command runs — the runtime behind
test.commandis installed (cargo/bun/nodeperruntime.packageManager). Fix: install it.
Warnings
- CI gates — the default branch has required status checks (
gh api repos/<repo>/branches/<default>/protection→required_status_checks.contextsnon-empty), and.github/workflows/has a test gate. Empty/absent → "merges aren't gated." Fix: add a test-gate workflow (see rig'sci/), then mark its check required. (manual — protection is sensitive) - shape labels exist — on
tracker: github, thetracker.shapeLabelsvalues exist as repo labels (gh label list). (--fix:gh label create.) - board columns match —
tracker.board.statusOptionsvalues exist as columns on the board (gh project field-list). Fix: add the columns, or correct the config. (--fix: add viaghif missing.) - review catalog —
review.patternsFile(default.claude/REVIEWER.md) exists. Fix: copy the template from rigtemplates/. (--fix: copy it in.) - writing-style guide —
style.guideFile(default.claude/STYLE.md) exists, so every agent writes PR bodies, tickets, and findings to one standard. Absent → "agent prose is unconstrained." Fix: copy the template from rigtemplates/. (--fix: copy it in.) - review bot reachable — if
review.bot≠none, the bot is installed on the repo. Fix: install it or setreview.bot: none.
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.
- 3d ago First seen · 100 lines · 105 tokens per session scan A c2f7813fc71b
rig-doctor is a skill published in the GitHub repository agent-rig/rig (2 stars, last pushed 16d ago), licensed MIT. It adds 105 tokens to every session and 1,403 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
infrastructure-project
Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.
organize-codex-projects
Choose a location and internal structure for a future Codex project, including focused projects and umbrella projects with durable subprojects. Use when creating or planning a new project. Do not move, rename, or normalize existing projects.
architectural-engineering-manager
Use when a task needs the judgment of an Architecture/Engineering firm or department manager — pricing a project fee (lump sum vs. hourly vs. % of construction cost), staffing a project against backlog, evaluating scope creep on a fixed-fee job, managing professional liability exposure, or deciding whether to pursue a…
archivist
Use when a task needs the judgment of an archivist — appraising whether a donated or transferred collection has enduring value, deciding a processing level for a backlog, writing a finding aid, triaging preservation under budget constraints, or resolving a records-restriction question.
repository-bootstrap
Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.
init-worktracking
Scaffold a portable, agent-optimized spec-driven work-tracking system into the current repository: AGENTS.md (global rules + agent reading protocol), a .tasks/ directory of atomic task files, and (by tier) ROADMAP.md, CHANGELOG.md, a validate.py checker, and thin CLAUDE.md/Cursor/Copilot pointers. Choose a footprint…