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 ronronner02/codepilot-agent --skill spec-worktreegit clone --depth 1 https://github.com/ronronner02/codepilot-agentWrote 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/ronronner02/codepilot-agent/spec-worktree)<a href="https://agentmods.dev/skills/ronronner02/codepilot-agent/spec-worktree"><img src="https://agentmods.dev/badge/skills/ronronner02/codepilot-agent/spec-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/ronronner02/codepilot-agent/spec-worktree"><img src="https://agentmods.dev/badge/skills/ronronner02/codepilot-agent/spec-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 | $0.00037 | $0.03042 |
| Opus 5.5 | $0.00015 | $0.01217 |
| Sonnet 5.5 | $0.00007 | $0.00608 |
| Haiku 4.5 | $0.00004 | $0.00304 |
Grade A, and why
spec-worktree scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree Isolation
Detect whether the current checkout is already isolated, then create or attach a worktree under .worktrees/<slug> only when isolation is still needed. The bundled script adds branch-specific setup that git worktree add alone does not handle:
- Does not copy
.env*files by default;--copy-envis an explicit opt-in for workflows that need local env files - Trusts
mise/direnvconfigs, with branch-aware safety rules so review branches do not auto-grant trust to untrusted.envrccontent - Adds
.worktreesto.gitignoreif not already ignored - Does not modify the main repo checkout —
from-branchand PR heads are fetched, not checked out
Step 0: Detect existing isolation
Before creating anything, invoke the bundled script with detect --json through the same bash -c wrapper whose command text includes exec bash ...worktree-manager.sh:
bash -c 'if [ -n "${CLAUDE_SKILL_DIR:-}" ]; then exec bash "$CLAUDE_SKILL_DIR/scripts/worktree-manager.sh" "$@"; fi; exec bash "$(git rev-parse --show-toplevel)"/".claude/skills/spec-worktree/scripts/worktree-manager.sh" "$@"' _ detect --json
The output is the deterministic facts contract spec-worktree-detect.v1:
{
"schema_version": "spec-worktree-detect.v1",
"state": "ordinary-checkout | linked-worktree | submodule | unknown",
"reason_code": "same-git-dir | linked-worktree | submodule-superproject | not-git-repo | git-query-failed | output-contract-failed",
"worktree_root": "<absolute path or null>",
"main_worktree_root": "<absolute path or null>",
"git_dir": "<resolved absolute path or null>",
"common_dir": "<resolved absolute path or null>",
"branch": "<current branch or null>"
}
state=ordinary-checkout and state=submodule mean creation may proceed if the workflow still needs isolation. For state=submodule, the new worktree is created under the submodule's own working tree (<submodule-root>/.worktrees/<branch>), not the superproject. state=linked-worktree means the current checkout is already isolated; report worktree_root and branch, then work in place instead of creating another worktree. state=unknown or any non-zero detect exit means stop and report reason_code; do not fall back to raw git worktree add.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 158 lines · 37 tokens per session scan A 4b0fcfd42936
spec-worktree is a skill published in the GitHub repository ronronner02/codepilot-agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 3,042 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
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
customize-setup
Set up personal AIWG customization mode from a local clone or fork — makes your clone the live global AIWG instance so edits go live immediately.
effect-ledger
Record an effect, sign an effect, reconcile an effect or check "did this PR merge" through the signed AIWG effect ledger, using one aiwg effect command with scriptable exit codes.
customize-contribute-back
Contribute a user's AIWG customization back upstream as a PR — reviews for general applicability, creates branch, opens PR.