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/holon-run/holon/agents-mdgit clone --depth 1 https://github.com/holon-run/holonWhat 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 | $0.00935 | $0.00935 |
| Opus 5 | $0.00467 | $0.00467 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
holon AGENTS.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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Holon is an early-stage headless runtime project. Keep the codebase small,
explicit, and easy to reason about.
Project Structure & Module Organization
src/: Rust runtime implementation and executable entrypoints.tests/: Rust integration tests and shared test support.builtin_templates/: runtime-managed agent templates.benchmark/andbenchmarks/: benchmark harness, fixtures, suites, and task manifests.docs/: current runtime contracts, architecture notes, and design records.holonbot/: Node-based GitHub App/bot retained as a separate service asset.skills/: repository skills that remain useful outside the old Go runtime.README.md: public-facing project definition.
Do not introduce large framework scaffolding before the runtime model is clear.
Product Intent
Holon is meant to be:
- headless
- event-driven
- long-lived
- explicit about trust boundaries
- explicit about user-facing versus internal output
When design choices conflict, prefer runtime clarity over convenience.
Development Priorities
Prioritize work in this order:
- Runtime model and message envelope.
- Queue, wake, sleep, and task lifecycle.
- Event ingress and trust classification.
- Structured user-facing output.
- Integrations and adapters.
Do not start with UI work unless the task explicitly requires it.
Coding Style & Naming Conventions
- Prefer simple, direct modules over indirection-heavy abstractions.
- Make state transitions explicit in code and types.
- Name modules after runtime responsibilities, not implementation accidents.
- Keep comments short and only where state or lifecycle behavior is non-obvious.
- Avoid hidden background behavior. If something wakes, retries, sleeps, or enqueues work, make that visible in names and logs.
Architecture Guardrails
- Treat
origin,trust, andpriorityas first-class runtime concepts. - Keep
briefor user-facing delivery separate from internal execution traces. - Do not mix operator input and external channel input without preserving provenance.
- Prefer append-only event/state logs when possible over opaque mutable state.
- Avoid coupling the core runtime to any single model vendor or UI surface.
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 · 109 lines · 935 tokens per session scan A ddf86903c2d4
holon AGENTS.md is an instructions file published in the GitHub repository holon-run/holon (134 stars, last pushed 3d ago), licensed Apache-2.0. It adds 935 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 2026-08-30.
Other instructions, from other repositories
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
DashClaw CLAUDE.md
Instructions for ucsandman/DashClaw, covering dashclaw (v2 governance runtime), commands, verify before you commit, gotchas (what you can't infer from the code) and governance boundary.
DashClaw AGENTS.md
Instructions for ucsandman/DashClaw, covering tooling note, design context, gitnexus — code intelligence, always do and never do.
DashClaw copilot-instructions.md
Instructions for ucsandman/DashClaw, covering dashclaw — github copilot instructions, design context, users, brand personality and aesthetic direction.
DashClaw GEMINI.md
Instructions for ucsandman/DashClaw, covering dashclaw development context, project overview, core product primitives, guard and action records.
bestie AGENTS.md
Instructions for sirquy/bestie, covering ai coding agent instructions, project state, current scope, architecture rules and safety and privacy.