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-tasknpx skills add agent-rig/rig --skill rig-taskgit clone --depth 1 https://github.com/agent-rig/rigWhat 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 | $0.00150 | $0.05190 |
| Opus 5 | $0.00075 | $0.02595 |
| Sonnet 5 | $0.00030 | $0.01038 |
| Haiku 4.5 | $0.00015 | $0.00519 |
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 yesterday.
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 — 337 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.
- yesterday First seen · 337 lines · 150 tokens per session scan A 3c5e46864902
rig-task is a skill published in the GitHub repository agent-rig/rig (2 stars, last pushed 14d ago), licensed MIT. It adds 150 tokens to every session and 5,190 once invoked, about $0.0007 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
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
engineering-wisdom
Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
product-decision-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B…
marketing-copy
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls to action, press-style announcements, and the naming of a product for another language or market. Covers what may be…
repo-health-check
Use when auditing a repo before changes to find the smallest safe PR, quality risks, stale docs, missing tests, ignored-file gaps, or agent setup issues. Best first skill for unfamiliar codebases.