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/danieljhkim/orbit/claude-mdgit clone --depth 1 https://github.com/danieljhkim/orbitWrote 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/danieljhkim/orbit/claude-md)<a href="https://agentmods.dev/instructions/danieljhkim/orbit/claude-md"><img src="https://agentmods.dev/badge/instructions/danieljhkim/orbit/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 | $0.01833 | $0.01833 |
| Opus 5 | $0.00916 | $0.00916 |
| Sonnet 5 | $0.00367 | $0.00367 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
orbit 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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orbit — agent guide
Project instructions for agents working on Orbit (loaded as both AGENTS.md and CLAUDE.md).
Rules
- Don't commit until the Orbit task has been explicitly approved by the human.
- Don't invent task IDs — get them from
orbit.task.add. Don't edit task files directly — useorbit.task.update. - Don't add cross-crate dependencies without checking and updating
ARCHITECTURE.md. If a new edge is genuinely needed, make its ownership and direction explicit in the same change. - Historical ADRs are being retired and are not an authority. Do not search for, cite, or use ADRs to justify a decision. Judge from the current code, runtime behavior, tests, documented constraints, and the requirements at hand.
Branching
mainis the release / production branch — only release merges and hotfixes land here. Default base for external install URLs, npm/Homebrew consumers, and the GitHub default-branch view.agent-mainis the dev integration branch — every task PR targetsagent-main.- Promotion: each release tags on
agent-main, then mergesagent-main → mainvia a merge commit. SeeRELEASING.md§10b. - Hotfixes branch from
main, merge tomain, tag a patch release onmain, then back-mergemain → agent-mainin the same session. SeeRELEASING.md§Hotfix flow.
Build / Lint
make ci-fast (fmt-check + guardrail scripts; no compile) and make ci-lint (the same workspace-wide, all-target clippy pass as CI, with warnings denied) must both pass before a task moves to review. Each task therefore pays for one workspace clippy compile; cold runs can take several minutes, while warm runs reuse Cargo's incremental cache. The full make ci is the canonical merge gate via .github/workflows/ci.yml on every PR — don't run it per task locally.
Architecture
Crate layering, per-crate responsibilities, and scoping rules live in ARCHITECTURE.md. Read it before adding a new crate, a new dependency edge, or a new persisted artifact.
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.
- 4d ago First seen · 98 lines · 1,833 tokens per session scan A d59ee0d47640
orbit CLAUDE.md is an instructions file published in the GitHub repository danieljhkim/orbit (10 stars, last pushed today), licensed MIT. It adds 1,833 tokens to every session, about $0.0092 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
anarlog AGENTS.md
AGENTS.md instructions for fastrepl/anarlog, covering commands, pre-commit verification, guidelines, code style and cli tui command architecture.
Lody AGENTS.md
AGENTS.md instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.
shodh-memory CLAUDE.md
Claude Code instructions for varun29ankuS/shodh-memory, covering shodh-memory project instructions, must rules, code standards, persistent memory (shodh-memory mcp) and codebase map.
Recall AGENTS.md
AGENTS.md instructions for samzong/Recall, covering agents.md, commands, architecture and boundaries.
hex AGENTS.md
AGENTS.md instructions for anomalyco/hex, covering hex agent guide, purpose, feature map, architecture and invariants.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.