Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.agents/skills/worktree/SKILL.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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/vanillagreencom/kendex/worktree)<a href="https://agentmods.dev/skills/vanillagreencom/kendex/worktree"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/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/vanillagreencom/kendex/worktree"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/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 | $0.00020 | $0.02463 |
| Opus 5.5 | $0.00008 | $0.00985 |
| Sonnet 5.5 | $0.00004 | $0.00493 |
| Haiku 4.5 | $0.00002 | $0.00246 |
Grade C, and why
worktree scanned grade C with 1 finding 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- kendex:project-instructions:start --> How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Problems with a kendex-owned skill go through kendex report; check ownership in the file first.
Worktree Management
.agents/skills/worktree/scripts/worktree <command> [options]
Worktrees live at <parent-of-checkout>/.worktrees/<checkout-name>/{id}, outside the repo root. A hosted lane's worktree lives at one path beside its clone instead, so a compile cache keyed by absolute source path hits across lanes: create --help, --hosted. Every command's contract is its --help: flags, exit codes, failure semantics, recovery. The top-level worktree --help carries the command index, path and issue-ID rules, configuration variables, and setup-path hardening.
Commands
| Command | Description |
|---|---|
create |
Claim a new issue worktree, a new-work claim, not a discovery command: existing ownership exits 75, and owned work is inspected or monitored, never given a second implementer. Reuse and conflict recovery: create --help |
restack |
Guardedly continue, skip, or abort a tool-created paused restack |
list |
List all worktrees |
remove |
Remove worktree, clean symlinks, prune branches |
cleanup |
Remove worktrees whose branches are merged; --targets-only prunes build output instead, keeping every worktree and branch |
path / exists |
Print / check the worktree path for an issue ID; path --hosted prints the hosted lane path |
merged |
Print the commit the issue tree's pull request merged as, asking about the branch that tree has checked out; exit 1 when none did, 2 when the lookup could not answer, a detached tree included (merged --help) |
check |
Pre-create git state check (JSON: uncommitted, unpushed) |
push |
Push worktree branch to remote. Publication, rebase, force-with-lease and rebase-map: contracts: push --help |
fix-links / repair-links |
Restore configured symlinks; repair-links is the git-hook-driven variant that never destroys untracked data |
codex-setup / codex-branch / codex-cleanup, claude-setup / claude-cleanup |
App-created worktree hooks. Installation wiring: references/hooks.md |
What ships with it
14 files 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.
- kendex.settings.toml.example 3.3 KB
- README.md 5.1 KB
- references/hooks.md 2.1 KB
- references/session-guard.md 4.3 KB
- scripts/lib/base-reading.sh 3.8 KB runs code
- scripts/lib/help.sh 56 KB runs code
- scripts/lib/kendex-env.sh 18 KB runs code
- scripts/lib/links.sh 61 KB runs code
- scripts/lib/messages.sh 353 B runs code
- scripts/lib/output-prune.sh 14 KB runs code
- scripts/lib/restack-state.sh 29 KB runs code
- scripts/worktree 217 KB
- scripts/worktree-output-prune 32 KB
- scripts/worktree-session-guard 23 KB
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.
- 5d ago Changed · +8 lines 4ca5dafe3cff
- 20d ago Changed e7624ba2458e
- 21d ago Changed · -1 lines b10c11b66fdc
- 22d ago Changed 759c35f91c4f
- 23d ago Changed · +2 lines 31a1da11b585
- 29d ago Changed · +2 lines b595f6f8402d
- 1mo ago Changed 8c5afad58df0
- 1mo ago Changed 36306aece3df
- 1mo ago Changed fd6f7f4ff7fc
- 1mo ago First seen · 89 lines · 20 tokens per session scan C d07ce937f79a
worktree is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 2,463 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rp
Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace. Covers workspace discovery, binding, root verification, and workspace hygiene.
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.
commit
A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
claude-md-improver
Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.