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 instructions/mercurialsolo/claudectl/claude-mdgit clone --depth 1 https://github.com/mercurialsolo/claudectlWrote 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/instructions/mercurialsolo/claudectl/claude-md)<a href="https://agentmods.dev/instructions/mercurialsolo/claudectl/claude-md"><img src="https://agentmods.dev/badge/instructions/mercurialsolo/claudectl/claude-md.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 5.1 | $0.04378 | $0.04378 |
| Opus 5 | $0.02189 | $0.02189 |
| Sonnet 5 | $0.00876 | $0.00876 |
| Haiku 4.5 | $0.00438 | $0.00438 |
Grade A, and why
claudectl 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 6d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claudectl
Orchestrate a swarm of Claude Code agents with a local-LLM brain that learns from you.
Build & Test
cargo build # Debug build
cargo build --release # Release build, default features (bus+coord+relay+hive) — ~6.3 MB; matches the Homebrew bottle
cargo build --release --no-default-features --features hive # Minimal sync-only build — ~3.5 MB
cargo test # Run all tests
cargo clippy -- -D warnings # Lint (warnings are errors in CI)
cargo fmt --check # Check formatting
Architecture
Workspace layout
This is a Cargo workspace with three crates. Dependencies flow strictly downward — claudectl → claudectl-tui → claudectl-core — and CI enforces it (Layering grep on core, plus standalone build jobs for each crate). Adding upward arrows is what the workspace exists to prevent.
crates/
├── claudectl-core/ # foundational types, IO, the UI↔runtime trait contract
│ # session, discovery, monitor, process, transcript,
│ # models, theme, logger, helpers, history, terminals/,
│ # health, rules, config, hooks, launch, skills, runtime
└── claudectl-tui/ # terminal UI + recording + demo fixtures
# app.rs, ui/*, recorder.rs, session_recorder.rs, demo.rs
# Depends on claudectl-core. Never on the binary.
src/ # the binary crate `claudectl`
# main.rs + brain/ + bus/ + coord/ + hive/ + relay/ +
# orchestrator + init + commands + config.rs +
# brain_screen.rs.
# Implements the runtime traits over the real
# subsystems via `src/runtime/`.
UI ↔ runtime contract lives at crates/claudectl-core/src/runtime.rs. Eight traits — SessionSource, BrainView, CoordView, BusView, Actions, BrainReviewView, Orchestrator, HiveActions, plus the stateful BrainDriver — wrapped in a Runtime aggregate. Core-owned DTOs (SessionSnapshot, DecisionSummary, LeaseSummary, HiveViewSnapshot, etc.) so the contract doesn't drag brain / coord / bus types upward. The binary's src/runtime/ provides Live* adapters that implement each trait over the real subsystem.
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.
- 6d ago First seen · 179 lines · 4,378 tokens per session scan A 2c2289ff9b4c
claudectl CLAUDE.md is an instructions file published in the GitHub repository mercurialsolo/claudectl (197 stars, last pushed 1mo ago), licensed MIT. It adds 4,378 tokens to every session, about $0.0219 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.
Other instructions, from other repositories
Codewhale AGENTS.md
AGENTS.md instructions for Hmbown/Codewhale, covering codewhale agent guidance, the ponytail method, working rules, landing other people's work and merging under a gate.
Codewhale CLAUDE.md
Claude Code instructions for Hmbown/Codewhale, a project described as: Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.
icron CLAUDE.md
Instructions for zebbern/icron, covering icron, architecture, key directories, built-in tools and commands.
workstreams disposable.instructions.md
Guidelines for writing code using IDisposable.