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/sleeplesshan/token-router/claude-mdgit clone --depth 1 https://github.com/sleeplesshan/token-routerWrote 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/sleeplesshan/token-router/claude-md)<a href="https://agentmods.dev/instructions/sleeplesshan/token-router/claude-md"><img src="https://agentmods.dev/badge/instructions/sleeplesshan/token-router/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 | $0.00323 | $0.00323 |
| Opus 5 | $0.00161 | $0.00161 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
token-router 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 5d 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.
What it actually says
token-router Claude Code Bootstrap
Use token-router to avoid loading oversized evidence or long routeable instruction references into Claude Code when the task only needs a focused slice.
Router Commands
For logs and stack traces:
OLLAMA_NUM_CTX=4096 OLLAMA_KEEP_ALIVE=0s \
python3 scripts/router.py error_log path/to/file.log --query "error or incident terms"
For long source files:
OLLAMA_NUM_CTX=4096 OLLAMA_KEEP_ALIVE=0s \
python3 scripts/router.py heavy_code path/to/file.py --query "bug or code-path terms"
For long routeable agent-context references such as detailed CLAUDE.md, AGENTS.md, GEMINI.md, .cursorrules, or agent-context/*.md files:
OLLAMA_NUM_CTX=4096 OLLAMA_KEEP_ALIVE=0s \
python3 scripts/router.py agent_context path/to/agent-context.md --query "task-specific rule terms"
Operating Rules
- Treat the local model as a line router, not as a summarizer.
- Analyze only the raw slices returned by the router.
- If a slice is too narrow, request or inspect wider nearby line ranges.
- Keep mandatory always-on Claude rules short. The router cannot reduce the token cost of a long
CLAUDE.mdafter Claude Code has already loaded it. - Put long task-specific Claude Code guidance in routeable reference files, then use
agent_contextwhen those details matter.
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.
- 5d ago First seen · 35 lines · 323 tokens per session scan A 1f47a6c8dd30
token-router CLAUDE.md is an instructions file published in the GitHub repository sleeplesshan/token-router (82 stars, last pushed 2mo ago), licensed MIT. It adds 323 tokens to every session, about $0.0016 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
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).
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.
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 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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.