agent-controller CLAUDE.md

Repository instructions for Claude Code, an AI coding assistant, working on the agent-controller project. They say to follow the shared AGENTS.md guide before making changes.

In plain words
What is it for?
Use them before editing files in the agent-controller repository.
Why use it?
They keep the assistant's project-specific behavior in one canonical guide and reduce conflicting instructions.

Instructions file

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/ccdevelopforfun/agent-controller/claude-md
Clone the repo
git clone --depth 1 https://github.com/CCDevelopForFun/agent-controller
Per session 59 This file is loaded in full into every session.
When invoked 59 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 $0.00059 $0.00059
Opus 5 $0.00030 $0.00030
Sonnet 5 $0.00012 $0.00012
Haiku 4.5 $0.00006 $0.00006

Measured 2d ago against content hash f2797bfa348d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-controller 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 2d 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.

CLAUDE.md · 9 lines

What it actually says

CLAUDE.md

Guidance for Claude Code working in this repository.

The canonical, tool-agnostic agent guide lives in AGENTS.md and is imported below so the two never drift. Read it before making changes.

@AGENTS.md

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. 2d ago First seen · 9 lines · 59 tokens per session scan A f2797bfa348d

Subscribe to this mod's changes

agent-controller CLAUDE.md is an instructions file published in the GitHub repository CCDevelopForFun/agent-controller (2 stars, last pushed 5d ago), licensed MIT. It adds 59 tokens to every session, 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.