agent-blueprint
llms.txt1 starsChanged 53 days agoMITView on GitHub
The universal blueprint and skill standard for AI coding agents — teaching LLMs how to think, audit, architect, and properly document any software project.
We split this llms.txt into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Never rewrite working systems unnecessarily.
- Distinctive: line 11
Every architectural decision needs an Architectural Decision Record (ADR).
- Distinctive: line 12
Every major change needs automated tests and must update living documentation in docs/.
≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# Agent Blueprint > The universal blueprint and skill standard for AI coding agents — teaching LLMs how to think, audit, architect, and properly document any software project. ## Core Rules for LLMs - The agent must adapt to the project. The project must not be forced to adapt to the skill. - Inspect before assuming. Understand existing architecture, dependencies, and state machines before editing. - Business logic comes before code structure. Security and data integrity come before features. - Deterministic tools before AI. Use AI only where reasoning adds unique value. - Never rewrite working systems unnecessarily. Preserve existing functionality unless explicitly deprecated. - Every architectural decision needs an Architectural Decision Record (ADR). - Every major change needs automated tests and must update living documentation in docs/. ## Key Documents - [AGENTS.md](AGENTS.md): Entry point and complete execution lifecycle for AI coding agents. - [Orchestrator](skills/00-orchestrator/SKILL.md): Project classification, technology detection, and skill activation. - [Discovery](skills/01-discovery/SKILL.md): Locating projects in monorepos or nested directories. - [Project Context](skills/02-project-context/SKILL.md): Inspecting frameworks, languages, databases, and dependencies. - [Business Architecture](skills/03-business-architecture/SKILL.md): Domain modeling, actor definitions, workflows, and state machines. - [Architecture](skills/04-architecture/SKILL.md): System boundaries, modular monoliths, and ADR templates. - [Documentation Standard](skills/05-documentation/SKILL.md): Living documentation framework (docs/ hierarchy). - [Codebase Audit](skills/06-codebase-audit/SKILL.md): Static code hygiene, patterns, and debt discovery. - [Security](skills/07-security/SKILL.md): Defense-in-depth, cryptographic hashing, CSRF, and rate limiting. - [Testing](skills/08-testing/SKILL.md): Test strategy, regression suites, and verification matrix. - [Performance](skills/09-performance/SKILL.md): Query optimization, caching, latency profiling. - [Full Audit](skills/10-audit/SKILL.md): Combined forensic audit workflow.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- 00-orchestratorSkill
- 01-discoverySkill
- 02-project-contextSkill
- 03-business-architectureSkill
- 04-architectureSkill
- 05-documentationSkill
- 06-codebase-auditSkill
- 07-securitySkill
- 08-testingSkill
- 09-performanceSkill
- 10-auditSkill
- 11-controlled-source-of-truthSkill
- 12-context-engineeringSkill
- 13-phase-loop-deliverySkill
- 14-forensics-and-debuggingSkill
- 15-autonomous-loop-and-simplificationSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.