AGENTS.mdA
AGENTS.md from product-on-purpose/thinking-framework-skills is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add product-on-purpose/thinking-framework-skills/AGENTS.md@git:20261018.bea29d3Pins git:20261018.bea29d3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- product-on-purpose/thinking-framework-skills
- Path
AGENTS.md- Versions recorded
- 8
- Latest version
- git:20261018.bea29d3, committed Oct 18, 2026
- First version recorded
- Jun 12, 2026
- Size
- 15,105 bytes
- Repository stars
- 21
- License
- Apache-2.0
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
# thinking-framework-skills - agent guide An evidence-graded library of agent-executable thinking-method skills, for AI agents and the humans who work with them. The plugin installs as `thinking-framework-skills`. Skill IDs are namespaced `thinking-framework-skills.<method>`, and installable skill names carry a `think-` prefix (for example `think-premortem`) to avoid cross-plugin collisions. Sibling to `pm-skills`, no technical coupling: `thinking-framework-skills` helps decide *what* to work on and *why* it is sound; `pm-skills` helps execute *how*. ## What makes a skill here different Each skill is built around four commitments, not just a prompt: 1. **Mechanism over ritual.** The skill implements the durable cognitive move, named descriptively, not a trademarked brand. 2. **Honest evidence grading.** Every skill carries an evidence tier and an `evidence/dossier.md` that says what the research does and does not support, and flags where evidence is transferred from human studies rather than validated for AI use. 3. **Artifact, not prose.** Every skill emits a concrete, reusable artifact (a risk register, an option matrix, a perspective review). …
Read the whole file at its exact version.
How to install
mdr add product-on-purpose/thinking-framework-skills/AGENTS.md@sha256:a37d34738e8ac969The line at the top of this page pins the label git:20261018.bea29d3, 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.
[](https://markdownregistry.com/a/art_563rguogbx77ixsl)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Jun 12, 2026 and Oct 18, 2026, about one every 18 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.bea29d3 latest | 2026-10-18 | bea29d3 | 15,105 B | A | view · diff |
| git:20261016.4688989 | 2026-10-16 | 4688989 | 14,531 B | A | view · diff |
| git:20261015.b3b6d98 | 2026-10-15 | b3b6d98 | 14,219 B | A | view · diff |
| git:20260621.67f523c | 2026-06-21 | 67f523c | 13,300 B | A | view · diff |
| git:20260620.c129d3c | 2026-06-20 | c129d3c | 12,912 B | A | view · diff |
| git:20260620.105aec4 | 2026-06-20 | 105aec4 | 12,174 B | A | view · diff |
| git:20260619.f4aa776 | 2026-06-19 | f4aa776 | 11,908 B | A | view · diff |
| git:20260612.8975a77 | 2026-06-12 | 8975a77 | 11,908 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (15105 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
product-on-purpose/thinking-framework-skills · 21 stars · license Apache-2.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_563rguogbx77ixsl GET https://markdownregistry.com/api/v1/resolve?ref=product-on-purpose/thinking-framework-skills/AGENTS.md GET https://markdownregistry.com/api/v1/blob/a37d34738e8ac969b6c8ec5bd8a2eec098e7bbc12f0317936bad64e9e36fdcb6
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 product-on-purpose/thinking-framework-skills
Every file in product-on-purpose/thinking-framework-skills