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 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/codician-team/growmos/integrations"><img src="https://agentmods.dev/badge/skills/codician-team/growmos/integrations.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00097 | $0.01044 |
| Opus 5.5 | $0.00039 | $0.00418 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 2mo ago), licensed MIT. It adds 97 tokens to every session and 1,044 once invoked, about $0.0004 per session on Opus 5.5. 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
A set of rules that makes an agent check its memory and available skills before handling professional tasks such as coding, file work, data analysis, or deployment.
agency-knowledge-graph-engineer
Structures information and capabilities into interconnected nodes (entities) and edges (relationships) — enabling dynamic context navigation, modular competency chaining, lower token costs, and hallucination reduction.
agency-example-workflow-with-memory
The Agency examples specialist.
dsh-archive-agent-notes
Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind}…
distill-session-knowledge
Offline-mine this project's pi session JSONL logs into reusable, verified knowledge: extracts faults, decisions, corrections, procedures and docs, promotes only recurring patterns, and routes artifacts into skillmanage, memory and docs. Use on "mine my sessions", "distill session knowledge", "extract lessons from…
akirule
Aki's contextual rule router — route EVERY task turn before acting, by what the task means (the domain it touches and the kind of act — write, decide, audit, ship), with listed signals as evidence, never as the test. Domains: code quality and structure (any code file), docs and any .md, UI copy and i18n, frontend…