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/qgolem/orc/claude-mdgit clone --depth 1 https://github.com/qGolem/orcWhat 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 | $0.01397 | $0.01397 |
| Opus 5 | $0.00698 | $0.00698 |
| Sonnet 5 | $0.00279 | $0.00279 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
orc 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
orc — Claude Code Plugin
Project Structure
This is a skills/agents plugin repo, not a conventional TypeScript project.
| Location | Contents |
|---|---|
skills/ |
Plugin skills (namespaced orc:) |
.claude/skills/ |
Local skills (no namespace) |
.claude/agents/ |
Agent definitions |
.claude/hooks/ |
Hook scripts (TypeScript, runs via Bun) |
.claude/context/ |
Generated codebase maps |
No src/ directory. Use tree -L 3 -P '*.md' skills/ or tree -L 2 .claude/ for structure.
Agents target multiple languages. When developing or testing agents, use the appropriate analysis tools:
| Purpose | TS/JS | Rust | Solidity |
|---|---|---|---|
| Dependencies | madge --circular src/ |
cargo modules dependencies --acyclic |
slither . --print inheritance-graph |
| Call chains | /dive symbol depth |
Grep-based tracing | slither . --print call-graph |
| Structure | file analysis | cargo modules structure --lib |
slither . --print contract-summary |
| Dep tree | madge --orphans src/ |
cargo tree --depth 2 |
forge inspect <C> storageLayout |
Runtime
Bun is the runtime. Use bun run, not npm run or pnpm run.
Hooks
Wiring
Hook registration requires BOTH:
- A script file under
.claude/hooks/(e.g.,index.ts) - An entry in
.claude/settings.jsonunder"hooks"
Always check both when debugging "hook didn't trigger."
Testing
Test hooks directly before claiming they work or don't:
echo '{"session_id":"test","transcript_path":"/tmp/t"}' | bun .claude/hooks/index.ts
Safety
.claude/hooks/index.tsis live — changes take immediate effect on the current session- Read the full file before editing; never infer content from memory or truncated reads
- Do not modify hook behavior without explicit request; hook logic is intentionally experimental
Deadlock
When a stop hook blocks and no user action resolves it within 2 turns:
- State the situation once with the exact user action required
- Stop repeating — no further substantive responses on that topic until user acts
- Never offer to commit as an escape hatch from a blocked state
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.
- 2d ago First seen · 121 lines · 1,397 tokens per session scan A 3703c55cb997
orc CLAUDE.md is an instructions file published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 1,397 tokens to every session, about $0.0070 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
workflow AGENTS.md
AGENTS.md instructions for vercel/workflow, covering agent instructions, architecture, core components, workflow execution model and development commands.
dxkit CLAUDE.md
Instructions for vyuh-labs/dxkit, covering claude.md — dxkit development rules, architecture rules, 1. tool invocation goes through the registry, 2. never duplicate tool invocation logic and 3. language facts come from detect.ts.
a-i--skills 03-development-workflow.instructions.md
Instructions for organvm-iv-taxis/a-i--skills, covering development workflow instructions, no repo-wide build system, common development commands, after adding/modifying skills and validation before committing.
team-shinchan AGENTS.md
Instructions for seokan-jeong/team-shinchan, covering agents.md - team-shinchan agent map, layer architecture, agent registry, call flow and quick reference.
devkit CLAUDE.md
Instructions for 5uck1ess/devkit, covering claude.md, layout, architectural invariants, conventions and fixing this file.
avvarre CLAUDE.md
Instructions for PralhadYadawad/avvarre, covering avvarre — claude code instructions, what is avvarre?, available slash commands, mcp tools and project memory (.avvarre/).