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/kampe/herdforge/claude-mdgit clone --depth 1 https://github.com/Kampe/HerdforgeWhat 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 | $0.00933 | $0.00933 |
| Opus 5 | $0.00466 | $0.00466 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
Herdforge CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Build Bootstrap & Routing Protocol
This document serves as the build bootstrap and routing specification for Claude and peer AI agents operating over Herdforge.
1. Quick Invariants (Hard Rules)
- Origin Main is Truth: Development occurs in worktrees or feature branches;
mainis always clean and green. - Fail-Closed Execution: Subcommands and API wrappers MUST exit non-zero on error. HTTP 200 responses containing
{"error": ...}JSON bodies are hard errors. - No Absolute Paths: Absolutely NO absolute paths in code, configs, or markdown. Use
./or$HERD_ROOT. - Deterministic Sorting: Candidate task queues MUST be sorted by $(\text{Priority DESC}, \text{Ticket Ref ASC})$.
- No AI Trailers in Commits: Never add
Co-Authored-By,Signed-off-by, or AI attribution trailers to git commits.
2. Fast Commands
# Build binary
make build
# Run preflight, unit tests, and build
make all
# Run self-test suite against active repository
make self-test
# Run unit tests across all packages
make test-unit
# Run preflight workspace boundary check
make preflight
# Launch interactive REPL shell
./bin/herd sh
# Execute pulse task claim sweep
./bin/herd pulse --role worker
3. Topic Routing Matrix
| Topic | Reference Document |
|---|---|
| Agent Skill & Integration Guide | SKILL.md / .herd/skills/herd.md |
| Agent Prompts & Contracts | .herd/prompts/ |
| Agent Governance & Invariants | AGENTS.md |
| Architecture & API Specs | docs/architecture/AGENT-IMPLEMENTATION-GUIDE.md |
| System RFC & Design | docs/rfcs/RFC-001-HERD-DAEMON.md |
Code intelligence: code-review-graph CLI
IMPORTANT: This project has a knowledge graph. ALWAYS use the
code-review-graph CLI BEFORE using Grep/Glob/Read to explore
the codebase. The graph is faster, cheaper (fewer tokens), and gives
you structural context (callers, dependents, test coverage) that file
scanning cannot.
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.
- 3d ago First seen · 92 lines · 933 tokens per session scan A 767d7aaaf3ef
Herdforge CLAUDE.md is an instructions file published in the GitHub repository Kampe/Herdforge (5 stars, last pushed 3d ago), licensed MIT. It adds 933 tokens to every session, about $0.0047 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 instructions, from other repositories
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.
ideate CLAUDE.md
Instructions for paultyng/ideate, covering claude.md — ideate, what this is, tech stack, project structure and build and run.
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
helmor AGENTS.md
Instructions for dohooo/helmor, covering agents.md, what is helmor, commands, architecture and three-process model.
homebutler CLAUDE.md
Instructions for Higangssh/homebutler, covering homebutler, verify before claiming anything works, writing commits, prs, and comments, no tool attribution and commit subjects.
sprawling AGENTS.md
Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.