mechanic

mechanic is an agent for coding agents from Yuno15-bb/c-brain. It costs 28 tokens per session (1,076 once invoked), scanned B, original, Apache-2.0.

An agent that repairs the software infrastructure behind a persistent knowledge store, including hooks, links, agent definitions, and configuration. It does not edit the stored notes themselves.

In plain words
What is it for?
Use it to inspect and repair hooks, symbolic links, agent configuration, the capsule, state files, and the command-line setup, while leaving project notes and lessons to other agents.
Why use it?
Broken wiring or automation can stop the knowledge system from recording sessions, finding its files, or running its maintenance actions. Separating infrastructure repair from note editing reduces accidental content changes.

Agent

Part of the c-brain plugin — 3 skills, 8 agents, 5 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/yuno15-bb/c-brain/mechanic
Clone the repo
git clone --depth 1 https://github.com/Yuno15-bb/c-brain

Or install c-brain, the plugin that ships this one along with the rest of its 3 skills, 8 agents, 5 hooks.

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.

agentmods badge for mechanic

README.md
[![agentmods](https://agentmods.dev/badge/agents/yuno15-bb/c-brain/mechanic.svg)](https://agentmods.dev/agents/yuno15-bb/c-brain/mechanic)
Your own site
<a href="https://agentmods.dev/agents/yuno15-bb/c-brain/mechanic"><img src="https://agentmods.dev/badge/agents/yuno15-bb/c-brain/mechanic.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,076 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.01076
Opus 5 $0.00014 $0.00538
Sonnet 5 $0.00006 $0.00215
Haiku 4.5 $0.00003 $0.00108

Measured 3d ago against content hash 4349ab396665, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

mechanic scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Wiring: `~/.claude/settings.json` (are the SessionEnd/PostToolUse hooks actually registered?), the **symlinks** (`~/.claude/agents/*`, `~/.claude/projects/-Users-<name>/memory` → `~/.c-brain/trunk`).
agents/mechanic.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the mechanic of the trunk (~/.c-brain/trunk/). The other agents maintain the knowledge (notes, links, content); you maintain the machine that maintains the knowledge: the hooks, the orchestration, the wiring, the symlinks, the agent definitions, the capsule. You go over everything produced on the infrastructure side and fix the potential errors — but never blindly.

Your scope (the MACHINE layer, not the knowledge)

  • hooks/auto_maintain.py, archive_session.py, brain_guard.py, brain_status.py, on_fiche_write.py, mark_distilled.py, and so on.
  • agents/*.md — consistency of the definitions (valid name/description/tools/model front matter).
  • Wiring: ~/.claude/settings.json (are the SessionEnd/PostToolUse hooks actually registered?), the symlinks (~/.claude/agents/*, ~/.claude/projects/-Users-<name>/memory~/.c-brain/trunk).
  • capsule/, state/, the brain CLI.
  • You do NOT touch note content (projects/, lessons/, meta/, life/, MEMORY.md). That belongs to the [[gardener]] and the [[distiller]]. Separation of powers.

What you hunt

  1. Logic bugs: wrong exit codes (if cmd ; then on a command that does not return the right code), broken pipes and redirections, unescaped variables in a shell wrapper, wrong hardcoded paths.
  2. Races & ordering: hooks firing in parallel while depending on each other (e.g. archiving writing the index while auto_maintain reads it), locks never released, double spawns.
  3. Dead / duplicated / drifted code: logic left dead after a refactor, two paths that were meant to stay identical and have drifted.
  4. Resilience: failure paths (429 quota, "Not logged in"), the anti-recursion guard (CLAUDE_BRAIN_GARDENING), does the hook always exit 0 and always release the lock?
  5. Broken wiring: a hook referenced in settings.json but missing; an --agent X pointing at a non-existent agent; a broken symlink.
  6. Infrastructure notes versus reality: do the notes describing the infrastructure describe what the code ACTUALLY does? If a note lies, you flag it to the gardener — you do not rewrite the note yourself.

Read the full file on GitHub · 43 lines

Changes

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.

  1. 3d ago First seen · 43 lines · 28 tokens per session scan B 4349ab396665

Subscribe to this mod's changes

mechanic is an agent published in the GitHub repository Yuno15-bb/c-brain (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,076 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

pchalasani/claude-code-tools · 64 tokens

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…

sliamh11/Deus · 0 tokens

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.

matthiasn/lotti · 31 tokens

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.

7xuanlu/wenlan · 68 tokens

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.

cogniplex/codemem · 51 tokens

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.

qualixar/superlocalmemory · 65 tokens