Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/codician-team/growmos/agents-mdgit clone --depth 1 https://github.com/codician-team/growmosWhat 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 | $0.00606 | $0.00606 |
| Opus 5 | $0.00303 | $0.00303 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
growmos AGENTS.md scanned grade A with 0 findings 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 3d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- growmos CLAUDE.md — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
growmos — living knowledge graph (shared memory for humans + agents)
This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance,
profiles, a journal). It is the shared world model that survives context windows. Treat it as
memory you read at the start of work and write to as you develop. Zero-config commands:
- Session start — run
growmos context(a compact brief: hubs, health, pending work, latest journal). If it lists pending work, run thegrowmos next→ apply loop (step 4) right away, without being asked — it is quick, needs no permission, and is how the graph stays alive. - Before cross-cutting questions ("what depends on X?", "why was Y decided?") — run
growmos query "<question>"; answer from the returned subgraph and cite edge ids. - When you learn or decide something durable (new component, architectural decision, ownership,
dependency, gotcha) — write it back immediately:
growmos remember "<Name>" --type <TYPE> --desc "<one grounded sentence>"growmos link "<A>" "<predicate>" "<B>"(short verb phrase predicates: "depends on", "replaces")growmos journal "<what changed and why>"
- Feed the organism — run
growmos next. It hands you a task packet (extraction / resolution / profile / gold set / review) with the exact prompt, the JSON shape, and thegrowmos apply …command. Do the judgment work yourself, write the JSON, apply it. Repeat untilgrowmos nextsays the graph is up to date — that loop covers everything, including the evaluation gold set and the periodic node review. If it reports the daily extraction cap, rungrowmos next --force(the cap only guards unattended runs). Never invent facts not in the source; every relation must connect two extracted entities. - Before claiming facts about the repo in a summary/report —
growmos check "<claim text>"grounds your claims against edges with provenance (evaluator–optimizer loop). - Session end —
growmos journal "<summary of the session>"so the next session picks up here.
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.
- 3d ago First seen · 34 lines · 606 tokens per session scan A 059ab0a46ef1
growmos AGENTS.md is an instructions file published in the GitHub repository codician-team/growmos (9 stars, last pushed 16d ago), licensed MIT. It adds 606 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
build_a_product_agent CLAUDE.md
Instructions for ADW-19/build_a_product_agent, covering claude.md, 项目本质（readme 概览之外）, 目录与编号规范, 文章写作规范（新增/修改文章时必须遵循） and 常用操作.
akidevrule GEMINI.md
Instructions for lacvietanh/akidevrule, covering gemini.md — ag rules bootstrap, 1. single source of truth and 2. separation of concerns.
akidevrule CLAUDE.md
Instructions for lacvietanh/akidevrule, covering akidevrule, project role, source of truth, file naming conventions and rule authoring principles.
starfleetctl AGENTS.md
AGENTS.md instructions for mpbt-hq/starfleetctl, a project described as: multi agent coordination / command & control toolkit following the Startrek fleet metaphor.
kungfu AGENTS.md
AGENTS.md instructions for kungfu-systems/kungfu, covering agents.md, start from the person's objective, rules that always apply, load bounded context before changing the repository and execute and verify through shifu.
kungfu CLAUDE.md
Claude Code instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before working in this repository. It routes both product use and contribution work to the repository sources of truth, including the requirement that development and build tasks enter through Shifu.