Borrowing it
Nothing to install: this file belongs to thomas-powers-jr/cadence. 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/thomas-powers-jr/cadence/main/.claude/skills/pr-land/SKILL.mdgit clone --depth 1 https://github.com/thomas-powers-jr/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/thomas-powers-jr/cadence/pr-land)<a href="https://agentmods.dev/skills/thomas-powers-jr/cadence/pr-land"><img src="https://agentmods.dev/badge/skills/thomas-powers-jr/cadence/pr-land/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/thomas-powers-jr/cadence/pr-land"><img src="https://agentmods.dev/badge/skills/thomas-powers-jr/cadence/pr-land.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 | $0.00080 | $0.00920 |
| Opus 5 | $0.00040 | $0.00460 |
| Sonnet 5 | $0.00016 | $0.00184 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
pr-land 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 12d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR land (protected main)
main requires the ci-success check and enforce_admins is on — there is
no direct-push path, for anyone. Everything lands branch → PR → green →
squash merge.
1 — Preflight locally (cheaper than a CI round-trip)
- Run
pnpm turbo run lint typecheck test buildbefore pushing. - Windows caveat: Linux CI is canonical. A few Windows-local test failures are known environment issues (pnpm/tempRepo/spawn races) — if something fails only locally and the failure smells environmental, push and let the CI matrix decide rather than debugging the dev box.
- Before any git operation that touches shared tree state —
stash,reset,checkoutontomain— re-checkgit statusimmediately beforehand, not from a check done minutes earlier in this same session. Another process (a subagent, a background build, a second terminal) can have changed the tree in between.
2 — Commit hygiene
- Stage explicitly, never
git add -A. Off-limits: live.cadence/state.jsonSTATE.mddirt mid-loop (the settle commit owns those),.agents/,launch/(local-only by explicit decision),.claude/scheduled_tasks.lock, stray uncommittedSESSION-*.mdhandoffs.
- Single-commit settle convention when a phase is closing: source + tests +
docs + phase artifacts land together in one commit, no separate
chore: settlecommit after it. - Feature PRs carry their
.changeset/*.md. Conventional-commit subject with the phase id:feat: <what> (phase NNN).
3 — Push + PR
git push -u origin <branch>
gh pr create --title "<subject>" --body "<what/why, invariants checked>"
One logical change per PR. The PR body ends with the standard
🤖 Generated with [Claude Code](https://claude.com/claude-code) footer.
4 — Babysit CI (the flake protocol)
- Watch with
gh pr checks <n> --watch(or pollgh pr checks <n>). - On red, get the failing leg + test before reacting:
gh run view <run-id> --log-failed | head -100. - Re-run once, without investigation, only when all three hold: a single
OS/Node leg is red, the diff can't plausibly touch the failing area, and
the failure matches a known flake (reference: macOS/Node22 timeout in
settle-codereview-convergence.test.ts; newnode --testsubprocess spawns under parallel load have flaked before). - Anything else — multiple legs, plausible relation to the diff, an unfamiliar failure, or a second red after the re-run — is real until proven otherwise: investigate, don't loop re-runs.
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.
- 12d ago First seen · 79 lines · 80 tokens per session scan A 7e1a72da7ca6
pr-land is a skill published in the GitHub repository thomas-powers-jr/cadence (2 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 920 once invoked, about $0.0004 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
argot-setup
Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…
finishing-a-development-branch
Use when implementation is complete, all tests pass, and the user needs to decide how to integrate the work - presents the integration candidates (merge locally, push and open a PR, push only, keep) and executes only the chosen one; never merges on its own.
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
ph-git
(PH) Use only for an explicit Git operation with scoped status, diff, and transport discipline.
gwm
Manage git worktrees across any repository with the gwm Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (gwm exec) or reclaim build artifacts (gwm clean), materialise a PR into a worktree (gwm review), drive a…
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…