llm agents instructions

68 tagged llm agents, measured the same way as everything else here.

Browse within: Multi-Agent 7

tigerless-labs/autoharness

Instructions file CodexOpenCode

Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…

1.4k 1mo ago A 2,201 tokens original MIT

TheGreenCedar/codex-autoresearch

Instructions file CodexOpenCode

Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.

836 3d ago A 2,034 tokens original Apache-2.0

a-evolve CLAUDE.md

03

A-EVO-Lab/a-evolve

Instructions file

Claude Code instructions for A-EVO-Lab/a-evolve, covering claude.md, project overview, repository structure, arc-agi-3 key concepts and game environment (arc-agi sdk).

765 10d ago A 1,475 tokens

MatanYemini/bitbucket-mcp

Instructions file

Instructions for MatanYemini/bitbucket-mcp, covering claude.md, project overview, development commands, build and run and testing and quality.

165 3mo ago A 1,261 tokens original MIT

cc10x CLAUDE.md

05

romiluz13/cc10x

Instructions file

Instructions for romiluz13/cc10x, covering cc10x orchestration (always on), complementary skills (work together with cc10x) and complementary skills (work together with cc10x).

164 29d ago A 516 tokens original MIT

SkillHone AGENTS.md

06

Tencent/SkillHone

Instructions file CodexOpenCode

AGENTS.md instructions for Tencent/SkillHone, covering agent guide, pick the right skill, typical optimization flow, data boundaries and seed boundary.

137 23d ago A 659 tokens

Raidriar7170/hermes-skilleval

Instructions file CodexOpenCode

Instructions for Raidriar7170/hermes-skilleval, a project described as: Verification-gated skill routing and self-improvement harness for Hermes-style agent skills.

127 1mo ago A 363 tokens original MIT

Taoidle/plan-cascade

Instructions file

Instructions for Taoidle/plan-cascade, covering claude.md, project overview, build & development commands, run tests (uv auto-creates venv and installs deps) and linting.

124 5mo ago A 1,231 tokens original MIT

openlegion-ai/openlegion

Instructions file CodexOpenCode

AGENTS.md instructions for openlegion-ai/openlegion, a project described as: Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do.

116 9d ago A 4 tokens

openlegion-ai/openlegion

Instructions file

Claude Code instructions for openlegion-ai/openlegion, covering claude.md — engine, commands & testing, git workflow, work patterns and architecture.

116 9d ago A 17,481 tokens

memv CLAUDE.md

11

vstorm-co/memv

Instructions file

Instructions for vstorm-co/memv, covering claude.md, project overview, development setup, commands and quality.

89 1mo ago A 1,576 tokens original MIT

synth-ai AGENTS.md

12

synth-laboratories/synth-ai

Instructions file CodexOpenCode

Instructions for synth-laboratories/synth-ai, covering project notes, critical: prod launch checklist, critical: managed research sdk ownership, coding style and critical: running the backend locally.

82 11d ago A 1,558 tokens original MIT

tensormux/kernel-skills

Instructions file

Claude Code instructions for tensormux/kernel-skills, covering claude.md, kernel-skills, repository mission, what this repository is and product scope for v1.

70 +1 2mo ago A 4,586 tokens original MIT

JingxuanC/causal-memory

Instructions file

Instructions for JingxuanC/causal-memory, covering causal memory mcp integration, causal memory integration, after acting on a decision and observing the result, when something fails unexpectedly and when a recorded lesson turns out to be wrong.

52 3d ago A 511 tokens original Apache-2.0

WhitzardAgent/WhitzardOS

Instructions file CodexOpenCode

Instructions for WhitzardAgent/WhitzardOS, covering qitos agents.md, repository purpose, architecture map, dependency rules and core engineering principles.

40 5d ago A 1,898 tokens original MIT

amiable-dev/llm-council

Instructions file

Instructions for amiable-dev/llm-council, covering claude.md — technical notes for llm council, project overview, running & developing, architecture: the l1→l4 layer model (adr-024) and module map (src/llmcouncil/).

39 5d ago A 10,730 tokens original MIT

qzc438/ontology-llm

Instructions file

Claude Code instructions for qzc438/ontology-llm, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

24 5d ago A 522 tokens

llm-wiki AGENTS.md

19

BogdanovychA/llm-wiki

Instructions file CodexOpenCode

Instructions for maintaining a personal wiki: a collection of linked knowledge pages built from source materials and organized by date and templates.

20 27d ago A 3,336 tokens original MIT

anthony-chaudhary/dos-kernel

Instructions file CodexOpenCode

Instructions for anthony-chaudhary/dos-kernel, covering what dos is (the 30-second version), run it yourself first — the 60-second proof, when the user asks you about dos (the consumer moves), build, test, and check your work and the layout in one screen.

19 8d ago A 4,444 tokens original MIT

anthony-chaudhary/dos-kernel

Instructions file

Instructions for anthony-chaudhary/dos-kernel, covering dos — the dispatch operating system, the layering — keep these apart, the syscall abi, install & test and dos on dos — dogfood the kernel here.

19 8d ago A 3,756 tokens original MIT

anthony-chaudhary/dos-kernel

Instructions file Gemini CLI

Instructions for anthony-chaudhary/dos-kernel, covering dos — the part that doesn't believe the agents, the rule, why this matters and setup.

19 8d ago A 606 tokens original MIT

Leehyunbin0131/claude-ros2-skills

Instructions file

Instructions for Leehyunbin0131/claude-ros2-skills, covering read this first — ros 2 verification protocol, establish before writing (no doc can tell you these) and done means it ran.

18 1mo ago A 643 tokens original Apache-2.0