rig-doctor

rig-doctor is a skill for Claude Code, Codex from agent-rig/rig. It costs 105 tokens per session (1,403 once invoked), scanned A, original, MIT.

A preflight checker for projects using Rig, reporting setup problems in the repository, tracker, board, configuration, and automated checks.

In plain words
What is it for?
Use it before working with Rig to check authentication, project-board access, configuration, CI checks, and the review catalogue.
Why use it?
It finds issues that could prevent Rig from working or leave changes without required checks or review. Each finding includes the exact fix, while changes require confirmation.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/agent-rig/rig/rig-doctor
Any agent
npx skills add agent-rig/rig --skill rig-doctor
Clone the repo
git clone --depth 1 https://github.com/agent-rig/rig

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for rig-doctor

README.md
[![agentmods](https://agentmods.dev/badge/skills/agent-rig/rig/rig-doctor.svg)](https://agentmods.dev/skills/agent-rig/rig/rig-doctor)
Your own site
<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>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash c2f7813fc71b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/rig-doctor/SKILL.md · 100 lines

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.providergithub or no tracker.board).

Checks

Blockers

  • gh present + authedgh --version, gh auth status. Fix: install https://cli.github.com / gh auth login. (manual — interactive)
  • project scope — when tracker.board is set, gh auth status must list project. Fix: gh auth refresh -s project --hostname github.com. (manual)
  • board reachablegh project view <n> --owner <owner> succeeds, and the adapter returns: run the resolved tracker adapter's select --limit 1 (.rig/rig-tracker if executable, else <RIG_DIR>/scripts/rig-tracker.sh). Fix: correct tracker.board.owner/projectNumber.
  • config valid.rig/config.json parses and matches rig.schema.json (.rig/schema.json). vcs.baseRef and vcs.defaultBranch exist on the remote (git ls-remote --heads origin <branch>). Fix: correct the fields.
  • test command runs — the runtime behind test.command is installed (cargo / bun / node per runtime.packageManager). Fix: install it.

Warnings

  • CI gates — the default branch has required status checks (gh api repos/<repo>/branches/<default>/protectionrequired_status_checks.contexts non-empty), and .github/workflows/ has a test gate. Empty/absent → "merges aren't gated." Fix: add a test-gate workflow (see rig's ci/), then mark its check required. (manual — protection is sensitive)
  • shape labels exist — on tracker: github, the tracker.shapeLabels values exist as repo labels (gh label list). (--fix: gh label create.)
  • board columns matchtracker.board.statusOptions values exist as columns on the board (gh project field-list). Fix: add the columns, or correct the config. (--fix: add via gh if missing.)
  • review catalogreview.patternsFile (default .claude/REVIEWER.md) exists. Fix: copy the template from rig templates/. (--fix: copy it in.)
  • writing-style guidestyle.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 rig templates/. (--fix: copy it in.)
  • review bot reachable — if review.botnone, the bot is installed on the repo. Fix: install it or set review.bot: none.

Read the full file on GitHub · 100 lines

Changes

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.

  1. 3d ago First seen · 100 lines · 105 tokens per session scan A c2f7813fc71b

Subscribe to this mod's changes

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.

Related

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.

docxology/template · 40 tokens

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.

WildPigKing/codex-project-skill-manager · 52 tokens

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…

wonsukchoi/domain-experts · 73 tokens

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.

wonsukchoi/domain-experts · 57 tokens

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.

cz1993/vibe-coding-repository-standard · 41 tokens

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…

hams-ollo/zen-agent-skills · 207 tokens