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-worktreenpx skills add agent-rig/rig --skill rig-worktreegit 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 | $0.00103 | $0.02149 |
| Opus 5 | $0.00051 | $0.01074 |
| Sonnet 5 | $0.00021 | $0.00430 |
| Haiku 4.5 | $0.00010 | $0.00215 |
Grade A, and why
rig-worktree 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree — isolated dev checkout lifecycle
Create / list / remove isolated git worktrees under .claude/worktrees/.
Creation produces a worktree that's actually ready to run: fetched from
origin, branched from the right base, env files symlinked, dependencies
installed. This is a shared bootstrap you can call directly (spikes,
ad-hoc branches, parallel experiments) and that implement-style flows and
prune/rig-tidy steps can delegate to.
The logic lives in two scripts so the invariants live in one place:
.claude/scripts/setup-worktree.sh (create) and
.claude/scripts/remove-worktree.sh (teardown). Creation encodes
three invariants that bite if skipped — fetch-before-branch (stale
local refs silently start you on a pre-merge tip), env symlinks (missing
secrets read as flaky/timeout test failures, not "config not found"),
and a per-worktree dependency install (installed deps don't carry across
worktrees → Cannot find package '...'). Don't reimplement these
inline; call the scripts.
Configuration
Reads .rig/config.json (missing keys → defaults):
| Key | Default | Used for |
|---|---|---|
vcs.baseRef |
origin/main |
Default --base the worktree branches from. |
vcs.branchConvention |
{user}/{ticket}-{slug} |
Template when inferring a branch name from a ticket ID. |
vcs.defaultBranch |
main |
The trunk (informational; the main worktree). |
runtime.installCommand |
derived from packageManager |
Passed to the setup script as --install-cmd. |
runtime.packageManager |
npm |
Derives the install command when installCommand is unset (bun→bun install, pnpm→pnpm install, yarn→yarn, npm→npm install, none→skip install). |
tracker.ticketPrefix |
— | Recognizing a ticket ID (e.g. ABC-521) to slot into the branch template. |
If .rig/config.json is absent, run unconfigured: base origin/main,
install npm install, branch template {user}/{ticket}-{slug}, and say so.
Subcommands
$ARGUMENTS routes to one of:
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 · 169 lines · 103 tokens per session scan A 8ba3ac18b499
rig-worktree is a skill published in the GitHub repository agent-rig/rig (2 stars, last pushed 14d ago), licensed MIT. It adds 103 tokens to every session and 2,149 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
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.