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 muhimu/claude-plan-lifecycle --skill reap-plansgit clone --depth 1 https://github.com/muhimu/claude-plan-lifecycleWrote 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/muhimu/claude-plan-lifecycle/reap-plans)<a href="https://agentmods.dev/skills/muhimu/claude-plan-lifecycle/reap-plans"><img src="https://agentmods.dev/badge/skills/muhimu/claude-plan-lifecycle/reap-plans/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/muhimu/claude-plan-lifecycle/reap-plans"><img src="https://agentmods.dev/badge/skills/muhimu/claude-plan-lifecycle/reap-plans.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 | $0.00039 | $0.00568 |
| Opus 5 | $0.00019 | $0.00284 |
| Sonnet 5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
reap-plans 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 10d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reap Plans
Archive implementation plans whose PRs have merged. The logic lives in the
reap-plans bash script (shipped in this plugin's bin/; it must be on PATH) — this skill wraps it with
the run order and the conventions the script relies on.
What the script does
Groups the plans dir's *.md by frontmatter slug: (a design + its impl plan reap
as one group), checks each group's pr: merge state via gh, and for MERGED
groups stamps status: merged into every member and moves them to
<plans-dir>/done/. Groups with no resolvable PR, or any status: abandoned
member, are left untouched.
How to run
Always dry-run first, then the real run:
reap-plans -n # show what would move, change nothing
reap-plans # stamp status: merged and move merged groups to done/
Run from the repo root. The script resolves the plans dir itself
(-d flag, else PLANS_DIR env, else git config plans.dir, else default
local/plans). Requires an authenticated gh. If the plans dir is tracked
in git, commit the moves it makes.
Read the dry-run output before the real run. Flag anything odd to the user:
UNKNOWN states (a PR number the script couldn't resolve), conflicting-PR
warnings, or a plan you expected to reap sitting in "no PR".
Conventions the script depends on
The frontmatter rules the script reads (slug, pr, status) are defined in
the plan-frontmatter skill — REQUIRED BACKGROUND: read it for the full
field spec. What matters for reaping:
pr:must resolve to a real PR. Empty (pr:) = no PR yet = work-in-progress, never reaped.status: mergedis script-owned. Never hand-write it — the script sets it from GitHub merge state so it can't drift. You setdraft/in-progress/abandonedonly.slug:groups a design + its impl plan so they reap together.
Do not
- Do not move plans to
done/by hand — run the script sostatus:is stamped. - Do not reap a group whose PR merge state you haven't confirmed in the dry 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.
- 10d ago First seen · 52 lines · 39 tokens per session scan A 7b73f15a1a13
reap-plans is a skill published in the GitHub repository muhimu/claude-plan-lifecycle (2 stars, last pushed 9d ago), licensed MIT. It adds 39 tokens to every session and 568 once invoked, about $0.0002 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.