reap

reap is a skill for Claude Code from thousandflowers/skillreaper. It costs 56 tokens per session (534 once invoked), scanned A, original, MIT.

A skill that reports which parts of the agent's loaded context were not used, based on real session transcripts. Context includes instructions, tools, hooks, and other information available to the agent.

In plain words
What is it for?
It is for generating a context-use report with the reap command, including unused skills, tool servers, subagents, hooks, and always-loaded text.
Why use it?
It helps explain why the context window is filling up and identify material that may be safe to remove.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents.

Part of the skillreaper plugin — 2 skills shipped together

Install

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.

agentmods
npx agentmods add skills/thousandflowers/skillreaper/reap
Any agent
npx skills add thousandflowers/skillreaper --skill reap
Clone the repo
git clone --depth 1 https://github.com/thousandflowers/skillreaper

Made for: Claude Code.

Or install skillreaper, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for reap

README.md
[![agentmods](https://agentmods.dev/badge/skills/thousandflowers/skillreaper/reap.svg)](https://agentmods.dev/skills/thousandflowers/skillreaper/reap)
Your own site
<a href="https://agentmods.dev/skills/thousandflowers/skillreaper/reap"><img src="https://agentmods.dev/badge/skills/thousandflowers/skillreaper/reap.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 534 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.00534
Opus 5 $0.00028 $0.00267
Sonnet 5 $0.00011 $0.00107
Haiku 4.5 $0.00006 $0.00053

Measured 6d ago against content hash 136155785687, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reap 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 6d 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.

plugins/skillreaper/skills/reap/SKILL.md · 60 lines

What it actually says

skillreaper - context utilization report

Run reap --agent, then paste its output verbatim.

Do not reformat, re-order, summarise, truncate or re-align anything, and do not add a heading or a table of your own: the binary already renders the report, including its closing attribution line.

Arguments

Append any $ARGUMENTS tokens that begin with -; ignore anything else and say so. --days N sets the evidence window (default 30), --model <id> prices it. For the full inventory rather than the top rows, use reap --json.

If reap is not installed

Decide with command -v reap and nothing else - never an absolute path, never a filesystem search: a copy found off PATH may be an older build, and silently using it hides a broken install.

If that fails, print exactly this and nothing else:

reap is not installed. Run it once without installing anything:

npx skillreaper

Or install it permanently:

brew install thousandflowers/tap/skillreaper
go install github.com/thousandflowers/skillreaper/cmd/reap@latest

If reap is too old

--agent needs reap ≥ 0.5.0. If it exits with flag provided but not defined: -agent, say the installed build is too old and give brew upgrade skillreaper (npm: npm install -g skillreaper@latest) - an upgrade, never the install block above, which they have already done.

Pruning

Never prune on your own initiative. reap prune is interactive and aborts when it has no terminal, so calling it from here does nothing anyway.

If the user explicitly asks in this turn: get an unambiguous yes, run reap prune --yes, and remind them of reap restore --all. If the request is at all ambiguous, hand them the plain reap prune command instead.

For the per-category breakdown, point them at /skillreaper:gap.

Changes

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.

  1. 6d ago First seen · 60 lines · 56 tokens per session scan A 136155785687

Subscribe to this mod's changes

reap is a skill published in the GitHub repository thousandflowers/skillreaper (56 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 534 once invoked, about $0.0003 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 2026-08-30.