AGENTS.mdA
AGENTS.md from cyberstrategyinstitute/ai-safe2-framework is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add cyberstrategyinstitute/ai-safe2-framework/AGENTS.md@git:20261023.53a59e2Pins git:20261023.53a59e2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- cyberstrategyinstitute/ai-safe2-framework
- Path
AGENTS.md- Versions recorded
- 22
- Latest version
- git:20261023.53a59e2, committed Oct 23, 2026
- First version recorded
- Aug 29, 2026
- Size
- 14,565 bytes
- Repository stars
- 158
- 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
# AI SAFE² v3.1 Agent Entry Point This file is the deterministic starting point for software agents, coding assistants, retrieval systems, compliance bots, and other automated consumers of this repository. It has two jobs: preserve correct framework interpretation and define the minimum evidence-producing workflow for changes made in this repository or by agents reusing these instructions elsewhere. ## Delivery workflow: isolate, build, prove, assess, ship Use this workflow with any model, harness, or review provider. Repository facts and executable evidence take priority over model confidence or reviewer scores. For material changes, classify delivery shape (`spike`, `bounded`, or `architectural`) separately from risk. Use `.ai-safe2/development-policy.json` and `safe2 dev plan` when the CLI is available. A generated plan or receipt is decision evidence, never merge, release, deployment, exception, policy-change, completion, or risk-acceptance authority. See `docs/engineering/AI-SAFE2-DEVELOPMENT-METHOD.md`. ### 1. Establish and isolate 1. Read the nearest applicable `AGENTS.md`, repository manifest, contributing …
Read the whole file at its exact version.
How to install
mdr add cyberstrategyinstitute/ai-safe2-framework/AGENTS.md@sha256:1f1bddd86d478cd0The line at the top of this page pins the label git:20261023.53a59e2, 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_el25ca7zewszxv4v)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 22 versions of this file, between Aug 29, 2026 and Oct 23, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261023.53a59e2 latest | 2026-10-23 | 53a59e2 | 14,565 B | A | view · diff |
| git:20261013.a4b349f | 2026-10-13 | a4b349f | 14,124 B | A | view · diff |
| git:20261013.60762ad | 2026-10-13 | 60762ad | 13,776 B | A | view · diff |
| git:20261013.bb538dc | 2026-10-13 | bb538dc | 13,776 B | A | view · diff |
| git:20261007.9f92160 | 2026-10-07 | 9f92160 | 13,776 B | A | view · diff |
| git:20261007.0d19fe0 | 2026-10-07 | 0d19fe0 | 13,779 B | A | view · diff |
| git:20261005.0dbedf4 | 2026-10-05 | 0dbedf4 | 13,754 B | A | view · diff |
| git:20261005.7f0a2e0 | 2026-10-05 | 7f0a2e0 | 13,664 B | A | view · diff |
| git:20261005.1c20926 | 2026-10-05 | 1c20926 | 13,577 B | A | view · diff |
| git:20261004.03f70c6 | 2026-10-04 | 03f70c6 | 13,575 B | A | view · diff |
| git:20261002.3a4cc32 | 2026-10-02 | 3a4cc32 | 13,508 B | A | view · diff |
| git:20261002.778fbc5 | 2026-10-02 | 778fbc5 | 13,524 B | A | view · diff |
| git:20261002.446e29a | 2026-10-02 | 446e29a | 12,528 B | A | view · diff |
| git:20261002.7cf6477 | 2026-10-02 | 7cf6477 | 12,544 B | A | view · diff |
| git:20261002.be2c819 | 2026-10-02 | be2c819 | 12,306 B | A | view · diff |
| git:20260923.aec8a51 | 2026-09-23 | aec8a51 | 11,298 B | A | view · diff |
| git:20260921.81e6477 | 2026-09-21 | 81e6477 | 11,239 B | A | view · diff |
| git:20260917.3709131 | 2026-09-17 | 3709131 | 11,239 B | A | view · diff |
| git:20260915.916bdc1 | 2026-09-15 | 916bdc1 | 10,778 B | A | view · diff |
| git:20260914.9dea3a7 | 2026-09-14 | 9dea3a7 | 4,550 B | A | view · diff |
| git:20260904.28aa1d8 | 2026-09-04 | 28aa1d8 | 4,479 B | A | view · diff |
| git:20260829.5a827c4 | 2026-08-29 | 5a827c4 | 4,183 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (14565 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
cyberstrategyinstitute/ai-safe2-framework · 158 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_el25ca7zewszxv4v GET https://markdownregistry.com/api/v1/resolve?ref=cyberstrategyinstitute/ai-safe2-framework/AGENTS.md GET https://markdownregistry.com/api/v1/blob/1f1bddd86d478cd0d0297bfd38ba13943735af45d0f5932f7ae1fa127c59f913
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 cyberstrategyinstitute/ai-safe2-framework
Every file in cyberstrategyinstitute/ai-safe2-framework