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/sentasity/cadence/c-worktreenpx skills add sentasity/cadence --skill c-worktreegit clone --depth 1 https://github.com/sentasity/cadenceWrote 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/sentasity/cadence/c-worktree)<a href="https://agentmods.dev/skills/sentasity/cadence/c-worktree"><img src="https://agentmods.dev/badge/skills/sentasity/cadence/c-worktree.svg" alt="Measured on agentmods" 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 | $0.00212 | $0.06094 |
| Opus 5 | $0.00106 | $0.03047 |
| Sonnet 5 | $0.00042 | $0.01219 |
| Haiku 4.5 | $0.00021 | $0.00609 |
Grade A, and why
c-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 4d 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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/c-worktree
You own the whole arc of an interactive worktree session: create → run dev server → go home through one of two exits (local merge or PR flow) → clean up, plus a deploy guard where a repo configures one. Generic where it can be (plain git plus a merge lock that works in any repo) and repo-aware only through optional config hooks. Pick the phase that matches the request — you rarely run all of them in one turn.
Invocation
/c-worktreeor/c-worktree create [<branch>]— create an isolated worktree (always asks for the base branch)./c-worktree merge [<feature>]— the local-merge exit: merge a feature branch home in this clone, lock-guarded. From a feature worktree with no arg, the current branch merges to its recorded parent; from the target worktree,<feature>merges into the current branch. When the branch's base is the repo's PR target, this first routes through the exit choice (see Two exits)./c-worktree pr [<feature>]— the PR-flow exit: push the branch and open a PR against its recorded parent; the worktree stays alive for review fixes, and cleanup runs after the PR merges./c-worktree cleanup [<feature>]— stop the dev server, remove the worktree, delete the branch, release the port. Detects a PR-shipped branch and verifies the PR merged first.
Bare phrasing maps to phases too: "new worktree" → create; "merge my branch back" / "I'm done, ship it" → the exit choice (see Two exits); "push this up" / "open a PR for this" → pr; "tear down this worktree" / "the PR merged, clean up" → cleanup.
The standalone-generic guarantee
/c-worktree requires no Cadence design, no plan, and no other /c-* skill
at runtime. It works in any git repo. With an empty or absent worktree: config
(or no .cadence/config.yaml at all), only the generic core runs: plain
git worktree add, a lock-guarded merge or a push + PR, and cleanup. The
references/merging.md menu and the merge lock (scripts/merge-lock.sh at the
plugin root) are the only non-trivial generic pieces. The PR-flow exit is
generic too: it needs a remote base (plus gh for the nicest path) and
degrades to push + a hand-opened PR when gh is absent.
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.
- 4d ago First seen · 413 lines · 0 tokens per session scan A 4787c7035763
c-worktree is a skill published in the GitHub repository sentasity/cadence (1 stars, last pushed 9d ago), licensed MIT. It adds 212 tokens to every session and 6,094 once invoked, about $0.0011 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
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.