Borrowing it
Nothing to install: this file belongs to itsamruth/subagent-reuse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/itsamruth/subagent-reuse/main/CLAUDE.mdgit clone --depth 1 https://github.com/itsamruth/subagent-reuseWrote 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/itsamruth/subagent-reuse/claude-md)<a href="https://agentmods.dev/instructions/itsamruth/subagent-reuse/claude-md"><img src="https://agentmods.dev/badge/instructions/itsamruth/subagent-reuse/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 | $0.00530 | $0.00530 |
| Opus 5 | $0.00265 | $0.00265 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
subagent-reuse 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 7d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Reuse Protocol
Rule
BEFORE spawning any subagent, call route_task first. Always.
Workflow
Before any subagent work
route_task(task, files?, directory?)
REUSE→ Callget_context(agent_id)to load what the agent knows. Checkstale_files— re-read any files that changed.CREATE_NEW→ Spawn a new subagent. If tip says torecall(), do that too.
Agent context is auto-discovered from Claude Code's native session storage. No manual registration needed.
Optional: augment auto-discovered context
log_work(agent_id, summary, files_read?, files_modified?, learnings?, output?)
Only needed if you want to add extra annotations beyond what the auto-scanner extracts.
When done
mark_done(agent_id)
Agent won't receive new routing but its logs remain searchable.
Example
User: "Fix the login redirect bug"
→ route_task("Fix login redirect bug after OAuth callback",
["src/auth/callback.ts", "src/middleware/session.ts"])
→ CREATE_NEW (no agent has context for these files)
→ ... agent reads files, fixes the bug ...
→ (context auto-extracted from native JSONL — no log_work needed)
User: "Now add refresh token rotation to the auth flow"
→ route_task("Add refresh token rotation to auth flow",
["src/auth/callback.ts", "src/auth/tokens.ts"])
→ REUSE agent_id (file overlap: callback.ts + same directory)
→ stale_files: [] (nothing changed)
→ get_context(agent_id)
→ Agent already knows the auth flow. No re-reading needed.
User: (edits callback.ts manually, then asks)
"Now fix the error handling in the callback"
→ route_task("Fix error handling in auth callback",
["src/auth/callback.ts"])
→ REUSE agent_id
→ stale_warning: "callback.ts changed since agent last read it. Re-read before modifying."
Staleness Detection
Each agent's known files are tracked via Merkle tree (SHA-256 content hashes). At routing time:
- Fresh files → full score weight
- Stale files (modified since agent read them) → half score weight
- Stale modifications (agent edited the file, but it changed after) → zero bonus
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.
- 7d ago First seen · 68 lines · 530 tokens per session scan A b98f556ab560
subagent-reuse CLAUDE.md is an instructions file published in the GitHub repository itsamruth/subagent-reuse (5 stars, last pushed 6mo ago), licensed MIT. It adds 530 tokens to every session, about $0.0027 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.