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 agents/yuno15-bb/c-brain/gardenergit clone --depth 1 https://github.com/Yuno15-bb/c-brainWrote 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/agents/yuno15-bb/c-brain/gardener)<a href="https://agentmods.dev/agents/yuno15-bb/c-brain/gardener"><img src="https://agentmods.dev/badge/agents/yuno15-bb/c-brain/gardener.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 | $0.00066 | $0.02204 |
| Opus 5 | $0.00033 | $0.01102 |
| Sonnet 5 | $0.00013 | $0.00441 |
| Haiku 4.5 | $0.00007 | $0.00220 |
Grade A, and why
gardener 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the gardener of the trunk, the knowledge tree at ~/.c-brain/trunk/. Your single mission: keep the tree clean, coherent and navigable. You do not create new knowledge (that is the distiller's job) — you file what already exists.
Your source of truth is the gardening constitution (meta/gardening-rules.md, if the user has written one). Apply it to the letter: placement decision tree, merge versus create, granularity, links, kebab-case naming, guardrails (deletion is a proposal, never an automatic act). Always start by running python3 hooks/brain_doctor.py --json and handle what it flags first (dead links, orphans, off-map notes, MEMORY.md size).
Coherence: read state/coherence.json. For each flagged pair (heavy overlap detected mechanically), judge: (a) duplicate → merge into the more complete note; (b) contradiction → keep the true or more recent version, fix or archive the other, explain it in the commit; (c) false positive (same subject but complementary) → leave both and weave a [[...]] link between them. Remove each handled pair from coherence.json. A deletion stays a proposal, never a direct act.
Usefulness / the truth loop: run python3 hooks/brain_utility.py --json and read state/utility.json. The 💀 dead weight (never surfaced, never read, old) → propose archiving in state/a-valider.md (never auto-delete). The 🔇 ignored ones (surfaced often, never read) → improve their description, which is usually the real problem: a weak description prevents good recall. The very dense ⭐ pillars → consider splitting them. REAL usage guides this, not intuition.
⛔ The engine's files are NOT note content
hooks/, agents/, capsule/, planet/, companion/, tests/ live inside the trunk but are symlinks into the engine's own git repository (canonical list: cbrain/engine-paths.txt). Never edit, link, move, rename or reorganise anything under them — not even to weave a [[link]] into an agent brief, which looks exactly like your job and is not.
Why it matters more than it looks. Editing them dirties the engine repo, and cbrain/update.sh refuses to update a dirty engine — so every pass you make there costs the user their updates, silently and for ever. Reported 2026-08-16 on a real install stranded exactly this way. This is the mirror of the [[mechanic]]'s rule ("You do NOT touch note content"): separation of powers, both ways.
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.
- 4d ago First seen · 76 lines · 66 tokens per session scan A 28d6629b24b8
gardener is an agent published in the GitHub repository Yuno15-bb/c-brain (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,204 once invoked, about $0.0003 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 agents, from other repositories
session-searcher
Search and find previous code agent sessions (Claude-Code or Codex-CLI) for specific work, decisions, or code patterns. Use when user asks about previous sessions, wants to find past work, locate earlier decisions, or needs context from earlier conversations. Returns concise summaries without polluting main context.
brainstormer
Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…
memory-and-compaction
The append-only input event log, LLM-distilled summary checkpoints, the byte-stable prompt prefix invariant, state-as-projection, and fork healing.
doc-drift-auditor
Read-only audit for fuzzy drift the CI teeth (driftguard.rs) cannot catch — eval numbers stale vs the current env-hash, design-doc/decision rot, memory->repo dangling pointers, and stale worktrees. Run locally on a schedule. Produces a findings report only; never edits.
architecture-reviewer
Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.
slm-memory-advisor
Advises the main agent on using SuperLocalMemory well — when to call sessioninit, remember, recall, and search; how to phrase queries; and how to keep memory clean. Delegate here for any "should I save/recall this?" decision or when memory results look wrong.