reap-evaluate

reap-evaluate is an agent for coding agents from c-d-cc/reap. It costs 24 tokens per session (2,391 once invoked), scanned B, original, no licence file.

An evaluation agent for independently checking results, assessing whether they fit their purpose, and managing goals across generations. The description does not define what “generation” means here.

In plain words
What is it for?
Use it to verify results, judge their fitness, and manage goals across repeated work cycles.
Why use it?
It provides a separate review of work and helps track whether broader goals remain aligned.

Agent

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 agents/c-d-cc/reap/reap-evaluate
Clone the repo
git clone --depth 1 https://github.com/c-d-cc/reap

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-evaluate

README.md
[![agentmods](https://agentmods.dev/badge/agents/c-d-cc/reap/reap-evaluate.svg)](https://agentmods.dev/agents/c-d-cc/reap/reap-evaluate)
Your own site
<a href="https://agentmods.dev/agents/c-d-cc/reap/reap-evaluate"><img src="https://agentmods.dev/badge/agents/c-d-cc/reap/reap-evaluate.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,391 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin unknown 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 $0.00024 $0.02391
Opus 5 $0.00012 $0.01196
Sonnet 5 $0.00005 $0.00478
Haiku 4.5 $0.00002 $0.00239

Measured today against content hash f2e51569507f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

reap-evaluate scanned grade B 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 today.

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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Do NOT run any command that modifies files, git state, or project state
src/templates/agents/reap-evaluate.md · 223 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. today Changed · -33 lines f2e51569507f
  2. 5d ago First seen · 256 lines · 24 tokens per session scan B 25e9f6226284

Subscribe to this mod's changes

reap-evaluate is an agent published in the GitHub repository c-d-cc/reap (55 stars, last pushed 3d ago), with no licence file. It adds 24 tokens to every session and 2,391 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.