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-sprintnpx skills add agent-rig/rig --skill rig-sprintgit 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 | $0.00133 | $0.02423 |
| Opus 5 | $0.00067 | $0.01211 |
| Sonnet 5 | $0.00027 | $0.00485 |
| Haiku 4.5 | $0.00013 | $0.00242 |
Grade A, and why
rig-sprint 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 2d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Orchestrator
A sprint is a batch of independent work items that each land on the trunk on their own. Use this when the work decomposes into pieces that don't interleave (no shared runtime contract across siblings, no half-migrated state if you ship one without the others). If children do interleave, use an epic / integration-branch flow instead — same decomposition step, plus a shared branch the children stack on.
Configuration
Reads .rig/config.json (missing keys → defaults):
| Key | Default | Used for |
|---|---|---|
tracker.provider |
none |
linear | github | none. Selects the ticket backend, or ad-hoc mode. |
tracker.team |
— | Linear team / GitHub org for list/create. |
tracker.project |
— | Linear project for list/create. |
tracker.ticketPrefix |
— | Recognize ticket IDs in $ARGUMENTS. |
tracker.githubIntegration |
false |
If true, GitHub drives PR/merge transitions; each /rig-task sets only the start-of-work In Progress. |
tracker.shapeLabels.sprint |
sprint |
GitHub-only label applied to each item at creation so a board/dispatcher can pick up sprint items. Omit shapeLabels to skip. |
vcs.baseRef |
origin/main |
Base each ticket's branch is cut from. |
vcs.branchConvention |
{user}/{ticket}-{slug} |
New-branch template. |
vcs.defaultBranch |
main |
Trunk each PR targets. |
vcs.protectedBranchMergeQueue |
false |
If true, merge via gh pr merge --auto and never pass --rebase/--squash. |
runtime.installCommand / packageManager |
npm |
Install command inside a worktree. |
test.command |
npm test |
Test step in each per-ticket implementation. |
sourceScope[0] |
src |
Default codebase area to explore during decomposition. |
style.guideFile |
.claude/STYLE.md |
Writing style for item titles, bodies, and the hand-off report. |
Tracker modes:
linear— tickets are Linear issues; use themcp__claude_ai_Linear__*tools.github— tickets are GitHub issues; usegh issue.none— ad-hoc mode. There are no ticket IDs. Treat each item in$ARGUMENTS(or each bullet the user gives) as a task description. Skip all create/list/move-ticket steps; the sprint operates directly on the task list, and each task's implementation opens a PR whose title is the task description.plan <feature>still decomposes into a numbered task list — it just prints it instead of creating tickets.
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.
- 2d ago First seen · 165 lines · 133 tokens per session scan A c8c0c711ceee
rig-sprint is a skill published in the GitHub repository agent-rig/rig (2 stars, last pushed 15d ago), licensed MIT. It adds 133 tokens to every session and 2,423 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
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.
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…
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
daily-brief
Start-of-day ranked brief - open issues, recent commits, work in progress, and anything waiting on a human decision. Use when asked for a 'daily brief', 'morning brief', 'what should I work on today', 'start my day', 'catch me up'.