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 SNIKO/agent-skills --skill swe-worktreegit clone --depth 1 https://github.com/SNIKO/agent-skillsWrote 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/sniko/agent-skills/swe-worktree)<a href="https://agentmods.dev/skills/sniko/agent-skills/swe-worktree"><img src="https://agentmods.dev/badge/skills/sniko/agent-skills/swe-worktree/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/sniko/agent-skills/swe-worktree"><img src="https://agentmods.dev/badge/skills/sniko/agent-skills/swe-worktree.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 | $0.00033 | $0.00969 |
| Opus 5.5 | $0.00013 | $0.00388 |
| Sonnet 5.5 | $0.00007 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
swe-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 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline
swe-shape → swe-spec → [swe-plan] → [swe-worktree] → swe-execute → swe-review, with swe-research available at any point.
Each stage runs in its own session: the user invokes one skill, reviews the result, clears the context, then invokes the next. Assume no memory of other stages beyond the files named below.
- This stage: optional infrastructure. Isolate the change before implementation.
- Reads: the change directory produced by earlier stages —
brief.md,spec.html, andplan.mdwhen present. Their contents are not needed; only their location. - Writes: a git branch and worktree, with the change directory copied into it.
- Next: the user runs
swe-executeinside the new worktree. Do not invoke it.
Purpose
Create a safe isolated branch and git worktree, copy the complete SWE change workspace into it, and report where implementation should continue. Worktrees are optional execution infrastructure, not a required specification stage.
Inputs
Infer from user input or an artifact path:
CHANGE_DIR:.swe/<change>/SLUG: kebab-case change labelREPO_NAME: repository root basenameBRANCH_NAME: repository convention, otherwise<slug>WORKTREE_PARENT: repository convention, otherwise../worktrees/<repo-name>/WORKTREE_PATH:<worktree-parent>/<slug>
Use the change directory named by the user. If it is ambiguous, ask which one to prepare.
The shared research corpus at .swe/research/ is not change scope. It is repository documentation that outlives any branch, so it is not copied and not branched: research produced during implementation is written to the corpus in the main working tree and committed independently. Copying it would fork the corpus per branch and guarantee divergence.
Workflow
- Inspect repository state. Read repository git guidance and inspect
git status --short, current branch, existing branches, and worktrees. Preserve unrelated changes. - Resolve names. Follow repository branch and worktree conventions. Fall back to the defaults above only when guidance is absent.
- Handle conflicts. If the branch or path already exists, report the exact conflict and ask whether to reuse it or choose another name.
- Create the worktree. Run:
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 First seen · 84 lines · 33 tokens per session scan A ef2973aa1576
swe-worktree is a skill published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 969 once invoked, about $0.0001 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
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
pr-description
Write or update a GitHub PR description a teammate understands in one quick read: a picture when one fits, then a few plain sentences grounded in the diff and real verification. Use when opening a PR or editing its description.
release-notes
Write release notes or a changelog entry that tell existing users what they will notice after updating, with the technical detail after it. Use when publishing a release, writing a changelog, or editing release notes.
vignette-todo-run
Run a batch of Vignette TODO items as a multi-agent worktree run. Use when Pete asks to "run the TODOs", "run items N to M", "do a todo run", or hands over queued items from docs/TODOS.md in the Vignette repo. The orchestrator plans, briefs, and reviews; delegated coding agents do every code change and every…
commit-context
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.
commit-history
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.