Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/claude-genasis/genasis/claude-md)<a href="https://agentmods.dev/instructions/claude-genasis/genasis/claude-md"><img src="https://agentmods.dev/badge/instructions/claude-genasis/genasis/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04742 | $0.04742 |
| Opus 5 | $0.02371 | $0.02371 |
| Sonnet 5 | $0.00948 | $0.00948 |
| Haiku 4.5 | $0.00474 | $0.00474 |
Grade A, and why
genasis CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `install.sh` — `curl` 로 받은 install.sh 본체 (테스트 산출물). How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Project Instructions for Genasis
This file is loaded automatically by Claude Code. It contains project-wide conventions and constraints that all agents / sessions must follow.
Core Philosophy — The North Star
Genasis exists to make AI agents first-class team members alongside humans by embedding them into the collaboration tools humans already use (Plane for issues, Mattermost for chat). Every feature, design decision, and code change must be evaluated against this mission:
-
Human-agent seamless collaboration: Agents must participate in the same messengers, issue boards, and sprint ceremonies that human team members use — not in a separate "AI sandbox." The goal is that a human reviewing a Plane board or Mattermost channel cannot (and need not) distinguish whether a given update came from a human or an agent.
-
Non-destructive adoption for existing teams: Teams already running agentic workflows (ECC, knowledge-work-plugins, claude-code-templates, custom
.claude/agents/) must be able to bolt Genasis on without rewriting their existing agent definitions. The overlay model (marker fences) exists precisely to honour this. -
Turnkey bootstrap for new teams: Teams with zero agentic experience must get a fully functional agentic team (
genasis init) that is immediately wired into Plane + Mattermost, ready to collaborate with humans from minute one. -
Agents operate through human-facing channels only: Every agent action (status update, question, code review request, blocker escalation) flows through the same Plane tickets and Mattermost threads that humans read. No hidden side-channels.
How to apply this philosophy
When proposing a new feature, refactor, or architectural change:
- Ask: "Does this bring agents closer to being natural team members in human collaboration tools?"
- If the answer is no, the proposal must include a justification for why the deviation serves the mission indirectly, or it should be rejected.
- If an alternative exists that better serves human-agent collaboration, propose it as a critical counter-suggestion — even if the original idea is technically elegant.
- Favour designs where a human PM, designer, or developer interacts with agents through the same UX they already use rather than through CLI-only or developer-only interfaces.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 353 lines · 4,742 tokens per session scan A 165d34d1020f
genasis CLAUDE.md is an instructions file published in the GitHub repository claude-genasis/genasis (7 stars, last pushed 3mo ago), licensed MIT. It adds 4,742 tokens to every session, about $0.0237 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
agent-sessions CLAUDE.md
Claude Code instructions for zenithpd/agent-sessions, a project described as: 🚀 Monitor your Claude Code sessions effortlessly on macOS with real-time status updates and quick access features for a streamlined development experience.
open-bridge AGENTS.md
AGENTS.md instructions for bks-lab/open-bridge, covering the bridge — agent instructions, required reading, session start detection (automatic), theme and agents.
jeff AGENTS.md
AGENTS.md instructions for johanthoren/jeff, covering agents.md: jeff, model expectation, the kitchen (persona), repo = the package and the method (how the system works).
kandev CLAUDE.md
Claude Code instructions for kdlbs/kandev, a project described as: AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.
babysitter CLAUDE.md
Claude Code instructions for a5c-ai/babysitter, covering claude.md, repo-specific overrides, read these first, quick commands and claude code local notes.
swarm-357 CLAUDE.md
Instructions for TechTideOhio/swarm-357, covering claude.md, what this repo is, python package (packages/techtide-swarm/), or from pypi and key classes.