AGENTS.md@packages/spec/src/commonA

AGENTS.md@packages/spec/src/common from haposoft/cafekit is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add haposoft/cafekit/packages/spec/src/common/AGENTS.md@git:20261023.a626d73

Pins git:20261023.a626d73 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
haposoft/cafekit
Path
packages/spec/src/common/AGENTS.md
Versions recorded
8
Latest version
git:20261023.a626d73, committed Oct 23, 2026
First version recorded
Aug 4, 2026
Size
2,384 bytes
Repository stars
54
License
none declared

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

# AGENTS.md

## Shared CafeKit instructions

- Deliver exactly what was asked. Do not expand, polish, or add optional work beyond the request. Match existing code style and structure.
- For process-first Specs, `plan.md` and flat `task-NN-*.md` files are
  canonical, hand-editable state. Each task has exactly one `Status:` field and
  keeps canonical execution proof in its final inline `## Receipt`.
- Specs uses three user decisions: GATE-SCOPE for scope, GATE-REVIEW for adversarial findings,
  and GATE-DONE for completion. Planning never starts implementation; implementation
  requires a new explicit user invocation. A vibe run the user invokes delegates these gates as the state-sync rule's vibe-run exception states.
- Synchronize only observed task state with surgical edits. Never invent proof,
  readiness, approval, review independence, or completed work.
- `NO_TESTS` and `0 tests + exit 0` do not pass when the task requires automated tests.
- When a hook blocks an action, that is an instruction boundary — do not work around it.
- Use conventional commits. Do not add AI attribution unless requested.

## Response style
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add haposoft/cafekit/packages/spec/src/common/AGENTS.md@sha256:1d242f8ac6b817b7

The line at the top of this page pins the label git:20261023.a626d73, 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_nqyb5i25i4qe7klm.svg)](https://markdownregistry.com/a/art_nqyb5i25i4qe7klm)

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

Versions

The registry has recorded 8 versions of this file, between Aug 4, 2026 and Oct 23, 2026, about one every 11 days.

versioncommittedcommitsizeaudit
git:20261023.a626d73 latest2026-10-23 a626d73 2,384 BA view · diff
git:20261007.8cdc9162026-10-07 8cdc916 2,282 BA view · diff
git:20260917.940cfd82026-09-17 940cfd8 2,409 BA view · diff
git:20260819.27b92812026-08-19 27b9281 2,385 BA view · diff
git:20260815.27e25f92026-08-15 27e25f9 2,145 BA view · diff
git:20260807.ae873f72026-08-07 ae873f7 1,953 BA view · diff
git:20260805.6f17b482026-08-05 6f17b48 1,588 BA view · diff
git:20260804.e4ca4f22026-08-04 e4ca4f2 1,480 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 (2384 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

haposoft/cafekit · 54 stars · license none declared · pushed 2026-11-05 · branch dev

API

GET https://markdownregistry.com/api/v1/artifacts/art_nqyb5i25i4qe7klm
GET https://markdownregistry.com/api/v1/resolve?ref=haposoft/cafekit/packages/spec/src/common/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/1d242f8ac6b817b7aa7a9296fc80926e4e073a8ee4a7a7f3995462518a589510

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 haposoft/cafekit

AGENTS.md AGENTS.md file
haposoft/cafekit · AGENTS.md
git:20261018.54f438e · audit A · 54 stars
CLAUDE.md CLAUDE.md file
haposoft/cafekit · CLAUDE.md
git:20261018.30be9bd · audit B · 54 stars
llms.txt@cafekit-web/src/components/ui llms.txt file
haposoft/cafekit · cafekit-web/src/components/ui/llms.txt
git:20260203.5213074 · audit A · 54 stars
CLAUDE.md@evals/research/fixtures/khong-luu-khong-sua CLAUDE.md file
haposoft/cafekit · evals/research/fixtures/khong-luu-khong-sua/CLAUDE.md
git:20260930.3fa9f43 · audit B · 54 stars
CLAUDE.md@packages/spec/src/claude CLAUDE.md file
haposoft/cafekit · packages/spec/src/claude/CLAUDE.md
git:20261023.a626d73 · audit B · 54 stars
cf:adv SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/adv/SKILL.md · Interview until the user and the agent hold the same picture of the outcome, preview it, then deliver honest…
v1.0.0 · audit A · 54 stars
cf:agent-browser SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/agent-browser/SKILL.md · AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying…
v1.0.0 · audit A · 54 stars
cf:ai-multimodal SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/ai-multimodal/SKILL.md · Analyze images/audio/video/documentation with Gemini API. Use for vision analysis, transcription, OCR, design…
v1.0.0 · audit A · 54 stars
cf:ask SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/ask/SKILL.md · Answer questions with evidence. Use when the user asks about project behavior, source code, specs, docs, configuration…
v1.0.0 · audit A · 54 stars
cf:backend-development SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/backend-development/SKILL.md · Build backends with Node.js, Python, Go (NestJS, FastAPI, Django). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT)…
v1.0.0 · audit A · 54 stars
cf:brainstorm SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/brainstorm/SKILL.md · Shape an unsettled piece of work into a decided one before anyone builds it. Use when the outcome is already agreed but…
v3.0.0 · audit A · 54 stars
cf:chrome-devtools SKILL.md skill
haposoft/cafekit · packages/spec/src/claude/skills/chrome-devtools/SKILL.md · Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis…
v1.1.0 · audit B · 54 stars

Every file in haposoft/cafekit

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