AGENTS.md@.capyA

AGENTS.md@.capy from serpro69/claude-toolbox is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add serpro69/claude-toolbox/.capy/AGENTS.md@git:20261021.5d0c5dd

Pins git:20261021.5d0c5dd in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
serpro69/claude-toolbox
Path
.capy/AGENTS.md
Versions recorded
11
Latest version
git:20261021.5d0c5dd, committed Oct 21, 2026
First version recorded
May 6, 2026
Size
13,894 bytes
Repository stars
151
License
a license file GitHub does not identify

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# capy — context-window routing

Capy captures execution output in a separate encrypted run store and returns bounded results. Knowledge and session search remain separate.

## Decision principle

Use capture for routine tests, builds and dependency installs. Codex enforces recognized commands for root and child agents; Claude Code receives guidance only. For other work, choose the tool based on what you need from the output:

- **Comprehension** (understand the full content) → direct tools (Bash, Read)
- **Extraction** (specific facts from large output) → capy tools

## When to use direct tools (Bash / Read)

- **Git commands:** diffs, logs, status, branch — always Bash. Diffs are comprehension content; BM25 fragments destroy review quality.
- **Small-output non-routine commands (<~50 lines):** ls, wc, file, git status — Bash directly. Sandbox overhead exceeds savings.
- **Files to comprehend or edit:** Read tool. Required before Edit.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add serpro69/claude-toolbox/.capy/AGENTS.md@sha256:0d521a149a943c6e

The line at the top of this page pins the label git:20261021.5d0c5dd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_hr6buiw2gonzz3d5.svg)](https://markdownregistry.com/a/art_hr6buiw2gonzz3d5)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 11 versions of this file, between May 6, 2026 and Oct 21, 2026, about one every 17 days.

versioncommittedcommitsizeaudit
git:20261021.5d0c5dd latest2026-10-21 5d0c5dd 13,894 BA view · diff
git:20261021.4bddfa92026-10-21 4bddfa9 14,403 BA view · diff
git:20261016.7e5ee752026-10-16 7e5ee75 11,075 BA view · diff
git:20260924.a6bab7f2026-09-24 a6bab7f 8,391 BA view · diff
git:20260913.6a0d0352026-09-13 6a0d035 7,825 BA view · diff
git:20260913.46212c72026-09-13 46212c7 7,798 BA view · diff
git:20260513.26667932026-05-13 2666793 7,068 BA view · diff
git:20260512.51b3c302026-05-12 51b3c30 7,095 BA view · diff
git:20260512.5c9d6a22026-05-12 5c9d6a2 7,281 BA view · diff
git:20260512.b88c0bf2026-05-12 b88c0bf 6,455 BA view · diff
git:20260506.6879a3b2026-05-06 6879a3b 6,260 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (13894 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

serpro69/claude-toolbox · 151 stars · license a license file GitHub does not identify · pushed 2026-10-22 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_hr6buiw2gonzz3d5
GET https://markdownregistry.com/api/v1/resolve?ref=serpro69/claude-toolbox/.capy/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/0d521a149a943c6e35eb50b474307523ed7c644f0616d19bae4a642b6d040441

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from serpro69/claude-toolbox

CLAUDE.md@.claude/toolbox CLAUDE.md file
serpro69/claude-toolbox · .claude/toolbox/CLAUDE.md
git:20260907.6d37633 · audit A · 151 stars
AGENTS.md AGENTS.md file
serpro69/claude-toolbox · AGENTS.md
git:20261020.3a15779 · audit A · 151 stars
CLAUDE.md CLAUDE.md file
serpro69/claude-toolbox · CLAUDE.md
git:20260907.94f4c46 · audit B · 151 stars
test-skill SKILL.md skill
serpro69/claude-toolbox · cmd/generate-kodex/testdata/source-plugin/skills/test-skill/SKILL.md · A test skill
git:20260427.c1181c6 · audit B · 151 stars
alpha SKILL.md skill
serpro69/claude-toolbox · cmd/plugin-graph/testdata/minimal-plugin/skills/alpha/SKILL.md
git:20260601.bccbbc6 · audit C · 151 stars
beta SKILL.md skill
serpro69/claude-toolbox · cmd/plugin-graph/testdata/minimal-plugin/skills/beta/SKILL.md
git:20260601.bccbbc6 · audit C · 151 stars
golang-security SKILL.md skill
serpro69/claude-toolbox · cmd/vendor-profiles/testdata/skills/golang-security/SKILL.md · A Go security skill for reviewing code
git:20260424.5ddff27 · audit B · 151 stars
golang-testing SKILL.md skill
serpro69/claude-toolbox · cmd/vendor-profiles/testdata/skills/golang-testing/SKILL.md · Go testing best practices
git:20260424.5ddff27 · audit B · 151 stars
brainstorm SKILL.md skill
serpro69/claude-toolbox · klaude-plugin/skills/brainstorm/SKILL.md · TRIGGER when: asked to brainstorm, think through, explore, or pressure-test a technical idea or decision through…
git:20261003.e6e8384 · audit A · 151 stars
chain-of-verification SKILL.md skill
serpro69/claude-toolbox · klaude-plugin/skills/chain-of-verification/SKILL.md · Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex…
git:20260605.d0fb1be · audit A · 151 stars
clarify-docs SKILL.md skill
serpro69/claude-toolbox · klaude-plugin/skills/clarify-docs/SKILL.md · TRIGGER when: asked to clarify or improve existing documentation, PR drafts or issue descriptions, including URLs and…
git:20261002.676752f · audit A · 151 stars
AGENTS.md@klaude-plugin/skills/clarify-docs/evals/agent-instruction-target/test-files AGENTS.md file
serpro69/claude-toolbox · klaude-plugin/skills/clarify-docs/evals/agent-instruction-target/test-files/AGENTS.md
git:20260930.473ee69 · audit B · 151 stars

Every file in serpro69/claude-toolbox

Browse by kind, by grade A, or by owner.