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 skills/codician-team/growmos/integrationsnpx skills add codician-team/growmos --skill integrationsgit clone --depth 1 https://github.com/codician-team/growmosWrote 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/skills/codician-team/growmos/integrations)<a href="https://agentmods.dev/skills/codician-team/growmos/integrations"><img src="https://agentmods.dev/badge/skills/codician-team/growmos/integrations.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 | $0.00097 | $0.01044 |
| Opus 5 | $0.00048 | $0.00522 |
| Sonnet 5 | $0.00019 | $0.00209 |
| Haiku 4.5 | $0.00010 | $0.00104 |
Grade A, and why
growmos 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.
This is a copy
100% identical to growmos — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
growmos — the repository's living knowledge graph
.growmos/ holds a knowledge graph built and maintained by agents and humans together:
canonical entities (typed nodes), relations (short-verb-phrase edges with provenance
and corroboration counts), profiles for hub nodes, a journal, and an evaluation
harness. It is the shared world model that survives context windows — read it first,
write to it as you develop.
The loop you run
| When | Command | What you do |
|---|---|---|
| Session start | growmos context |
Read the brief (hubs, health, pending, journal tail). |
| Cross-cutting question | growmos query "…" [--seed X] [--hops 2] |
Answer only from the returned triples; cite edge ids like [r_ab12…]; say what the graph lacks. |
| Something durable learned | growmos remember, growmos link, growmos journal |
Write it back with a grounded one-sentence description. |
| Graph needs feeding | growmos next |
You get a task packet: prompt + JSON schema + apply command. Produce the JSON, run the apply command. Repeat. |
| About to assert facts | growmos check "<text>" |
Verify claims against edges with provenance; escalate absent claims to the human. |
| Session end | growmos journal "…" |
Leave the next session a note. |
Rules for the judgment stages (from the Anthropic knowledge-graph playbook)
Extraction packet — extract only entities central to the document; write a one-sentence description grounded in this document (it is the disambiguation signal for resolution); predicates are short verb phrases ("commanded", "depends on", "part of"); every relation must connect two entities you extracted; never invent facts. Precision beats recall: a wrong entity spawns wrong edges that mislead multi-hop reasoning.
Resolution packet — cluster surface forms of the same real-world entity. Every input name appears in exactly one cluster; genuinely distinct entities get single-element clusters; use the descriptions, not just string similarity ("Edwin Aldrin" = "Buzz Aldrin"; "Gemini 12" ≠ "Project Gemini"); canonical = most complete unambiguous form.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 74 lines · 97 tokens per session scan A c2c0e29e4d6e
growmos is a skill published in the GitHub repository codician-team/growmos (9 stars, last pushed 17d ago), licensed MIT. It adds 97 tokens to every session and 1,044 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to growmos, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
skills-constitution
当 Agent 接到专业任务（编码/爬虫/文件操作/API调用/数据分析/文档/部署/推送等）时，强制先查记忆层和技能索引，有匹配必用、无匹配必搜、答复时自动推荐（排除已装）。用于防止 Agent 跳过技能直接硬扛通用能力。跨平台通用（WorkBuddy/Claude/ChatGPT/Cursor/Gemini 等 20+ 框架）。完整版本史见 CHANGELOG.md。.
akirule
Aki's contextual rule router — invoke BEFORE acting whenever the task touches any of - .md/.vue/.css/.tsx/.rs/.sql files; docs, plan, README, CHANGELOG; UI, component, CSS, tailwind; SEO, schema, sitemap; release, version, commit, push, deploy; DB schema, migration; Tauri; i18n, UI copy; pricing, biz; UX review…
akigitcommit
Analyze the working tree and commit changes in clean logical groups. Triages a long half-finished tree first (finished vs mid-edit vs abandoned vs accidental) before grouping. Auto-detects CHANGELOG to switch between domain-grouped mode (3–5 commits by object/feature) and type-grouped mode (feat/fix/refactor). Stages…
akidevsync-notes
Read and edit a project's .akidevsync/notes.json task/note file — the per-project task list written by the Aki-Dev-Sync app (github.com/lacvietanh/aki-dev-sync). Use when the user asks to list, add, pin/unpin, mark done, edit, or delete a task in that file, or mentions "task note", "note ghim", "pin task", "mark…
akilint
Mechanical format lint for the penalty-card classes of RULE-agent-behavior.md §0 — hard-wrapped code comments and markdown prose ([WRAP]) and oversize comments ([YAP]) — via the shared scythe.py detector. Deterministic file:line output; judgment stays with the session. Use when the user asks to lint/quét formatting…
akihelp
Introduce the whole Aki Claude Code system — installed skills, the akirule passive rule router (3 tiers), the deep-think passive/active split, and a painpoint-to-prompt table for the situations people actually hit — by reading live installed state, never a hardcoded inventory. Use when the user asks what Aki…