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 agent-rig/rig --skill rig-taskgit 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-task)<a href="https://agentmods.dev/skills/agent-rig/rig/rig-task"><img src="https://agentmods.dev/badge/skills/agent-rig/rig/rig-task/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/agent-rig/rig/rig-task"><img src="https://agentmods.dev/badge/skills/agent-rig/rig/rig-task.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 | $0.00150 | $0.06292 |
| Opus 5.5 | $0.00060 | $0.02517 |
| Sonnet 5.5 | $0.00030 | $0.01258 |
| Haiku 4.5 | $0.00015 | $0.00629 |
Grade A, and why
rig-task 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 1mo 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rig-task — implement one unit of work end-to-end
Take a single unit of work — a tracker issue or an ad-hoc "implement this"
with no issue filed — code it test-first, open a PR, drive it to a clean review,
and hand back. Never auto-merges unless --auto-merge is passed (then CI
gates the merge — see Step 5). This is the orchestrator over the kit's
building blocks: it delegates isolation to /rig-worktree, review to
/rig-review, and the fix loop to /rig-review fix, so each concern lives in
one place.
It's the single-unit sibling of /rig-epic (one unit vs many interleaved), and
mirrors its lifecycle: start gets you to an open PR, finish drives
the review to clean. By default a bare invocation runs both in one continuous
session — the phases exist for when you want to open the PR, let CI / the review
bot run, and finish later. /rig-sprint calls this once per item.
Configuration
Reads .rig/config.json (defaults in parentheses):
tracker.provider—linear|github|none(none). Selects how the spec is loaded and the PR is linked.none→ the item is an ad-hoc task description; no ticket calls.tracker.ticketPrefix— e.g.ABC-; used to infer a ticket from the branch.tracker.githubIntegration— whentrue, GitHub drives PR/merge transitions (In Review, Done); rig still sets the start-of-work "In Progress" (Step 1), which GitHub can't observe before a PR exists. Whenfalse/absent, you may move states freely.tracker.labelMapFile(.claude/label-mapping.md) — label source of truth.tracker.board— GitHub Projects v2 identity (owner, projectNumber, statusOptions, closingKeyword). Used at PR-open (Step 4) to link the PR and move the board via therig-trackeradapter. Absent → no board steps.vcs.baseRef(origin/main),vcs.defaultBranch(main),vcs.branchConvention({user}/{ticket}-{slug}),vcs.protectedBranchMergeQueue(false).runtime.packageManager/runtime.installCommand— passed to/rig-worktree.test.command(npm test),test.integrationCommand,test.e2eCommand.review.patternsFile(.claude/REVIEWER.md),review.bot(none),review.botRetrigger,review.maxRounds(5).style.guideFile(.claude/STYLE.md) — the house style for the commit message, the PR body, and the hand-back line.agents.architect/agents.qa/agents.coder/agents.reviewer(defaultrig-<role>) — the registered agent names for each role.
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.
- 1mo ago Changed · +65 lines d0ca8d453909
- 1mo ago First seen · 337 lines · 150 tokens per session scan A 3c5e46864902
rig-task is a skill published in the GitHub repository agent-rig/rig (3 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 6,292 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
agnostic-ai-gh-issue
Take one GitHub issue from branch to merged PR with TDD. Use when asked to work, fix, or implement an issue by number.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
nw-quality-framework
Quality gates - 11 commit readiness gates, build/test protocol, validation checkpoints, and quality metrics.
cmux-testing
Choose scoped cmux verification, add behavioral tests, and validate Swift test targets and wiring. Use when adding tests or deciding what local/CI evidence a change needs.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
resolve-issues
Resolves GitHub issues using isolated worktrees and test-driven development, then delegates PR creation to /github:create-pr so the quality gate and the /github:review-pr loop always run. This skill should be used when the user asks to "resolve an issue", "fix issue.