agentmods.dev

code-brain CLAUDE.md

Instructions for an agent working in the code-brain repository, covering how it should inspect code, plan changes, manage branches, respond, and verify its work. A repository is a project's files and version-controlled history.

In plain words
What is it for?
Use it to guide code-brain development tasks such as locating relevant code, editing the smallest necessary area, working on the correct branch, and checking results before reporting completion.
Why use it?
It gives the agent a consistent working contract, including how to preserve existing changes and avoid claiming success without verification. It also sets concise response and branch-handling rules.

Instructions file

11 2d ago A scan 904 tokens original Apache-2.0
View the source file ezBuilder/code-brain
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 instructions/ezbuilder/code-brain/claude-md
Clone the repo
git clone --depth 1 https://github.com/ezBuilder/code-brain
Per session 904 This file is loaded in full into every session.
When invoked 904 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00904 $0.00904
Opus 5 $0.00452 $0.00452
Sonnet 5 $0.00181 $0.00181
Haiku 4.5 $0.00090 $0.00090

Measured yesterday against content hash 73f11a75fae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-brain CLAUDE.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 yesterday.

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.

CLAUDE.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Brain Agent Contract

.ai/ owns repo-local agent context, memory, generated metadata, trust, and runtime tooling.

Response

  • Match the user's language unless they request otherwise.
  • Keep self-initiated progress/output under 10 words.
  • Keep answers concise by default.
  • When changes are broad, end with a brief key-point summary of outcome, verification, and remaining risk; do not narrate every edit.
  • Expand beyond these defaults only for explicit detail, severe error/risk, or required question.
  • No progress narration or next-step outro; continue until done, blocked, or approval is required.

Branches

  • Work on develop by default.
  • Never commit or push main unless the user explicitly requests main.
  • Do not create branches unless asked.
  • After a requested main merge, return to develop.

Loop

  1. Understand the request.
  2. Inspect local rules and current git state.
  3. Locate code with Code Brain before broad shell search.
  4. Before editing existing files, read exact target slices with hashline.
  5. Preserve unrelated user changes.
  6. Make the smallest coherent change.
  7. Verify before claiming success.
  8. Record durable decisions/todos when useful.

Planning

  • Plan first only when scope or impact is unclear.
  • Single-file fixes and explicit user-scoped work can proceed directly.
  • If new risk appears, stop only when approval or a decision is required.

Search Routing

  • Exact symbols, paths, and fast live checks: targeted rg or native file tools first.
  • Semantic discovery: MCP code_query first when its index is fresh and the target language is supported; use context_pack only when bounded richer context is needed.
  • If indexed retrieval is stale, empty, or low-confidence, continue with targeted native search; retrieval output is a lead, not proof.
  • Call graph: code_graph_callers, code_graph_callees, code_graph_symbol.
  • Before editing existing files, read exact target slices: code_read_hashline; CLI fallback: .ai/bin/ai code read-hashline PATH --start START --end END.
  • Long output or broad search: MCP sandbox_execute or .ai/bin/ai exec run -- ....
  • Direct broad shell grep -r, rg ., find, tree, ack, ag, git grep is last resort; keep native fallbacks targeted.

Read the full file on GitHub · 86 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. yesterday First seen · 86 lines · 904 tokens per session scan A 73f11a75fae9

Subscribe to this mod's changes

code-brain CLAUDE.md is an instructions file published in the GitHub repository ezBuilder/code-brain (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 904 tokens to every session, about $0.0045 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 2026-08-30.

Git and workflowMemory and contextResearchagent-memoryai-agentsai-toolsautomationclaude-codecode-search
Related

Other instructions, from other repositories

agentic-context-engine AGENTS.md

Instructions for kayba-ai/agentic-context-engine, covering agents.md, repository guidelines, pipeline-first development (mandatory), core code protection and documentation maintenance.

kayba-ai/agentic-context-engine · 1,359 tokens

graymatter AGENTS.md

Instructions for angelnicolasc/graymatter, covering agents.md, your tools, when to call which, first call and identity.

angelnicolasc/graymatter · 1,001 tokens

graymatter CLAUDE.md

Instructions for angelnicolasc/graymatter, covering claude.md, a user asked you to set graymatter up, you are working in a project that already uses graymatter and you are contributing to graymatter itself.

angelnicolasc/graymatter · 615 tokens

mnemon AGENTS.md

Instructions for mnemon-dev/mnemon, covering mnemon agent guidelines, development, go engineering and commit discipline.

mnemon-dev/mnemon · 611 tokens

mnemon CLAUDE.md

Instructions for mnemon-dev/mnemon, covering mnemon — project guidelines and development.

mnemon-dev/mnemon · 112 tokens

amfs CLAUDE.md

Instructions for raia-live/amfs, covering amfs memory — agent instructions, available mcp tools, identity, brain tools (agent-scoped) and shared knowledge tools.

raia-live/amfs · 2,185 tokens