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/elijas/token-throttle/claude-mdgit clone --depth 1 https://github.com/Elijas/token-throttleWrote 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/elijas/token-throttle/claude-md)<a href="https://agentmods.dev/instructions/elijas/token-throttle/claude-md"><img src="https://agentmods.dev/badge/instructions/elijas/token-throttle/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 | $0.00894 | $0.00894 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
token-throttle 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
token-throttle
Releasing a New Version
Releases are fully automated via GitHub Actions. Do NOT bump versions or publish locally.
Trigger a release
gh workflow run release.yml --ref main -f bump=patch # 0.5.0 -> 0.5.1
gh workflow run release.yml --ref main -f bump=minor # 0.5.0 -> 0.6.0
gh workflow run release.yml --ref main -f bump=major # 0.6.0 -> 1.0.0
What the workflow does
- Verifies manual dispatch is running from
refs/heads/mainwith a non-emptybumpinput, then runs full CI test suite (.github/workflows/ci.yml) bump-my-version bump <patch|minor|major>— updates version inpyproject.tomlandtoken_throttle/__init__.py, creates a commitdevtools/bump_readme_version.py— updates pip install version bounds in README.mduv lock— syncsuv.lockwith the new versionruff check --fix,ruff format, thenruff check— applies safe lint autofixes, formats, and fails if issues remain- Creates a second commit with lockfile/formatting changes (if any)
- Porcelain check — fails the release if the working tree is still dirty after all fixes
- Creates an annotated
vX.Y.Ztag and atomically pushesmainplus the tag - Internally re-dispatches
release.ymlon the immutable tag - Re-runs full CI test suite on the tag
- Runs
uv buildbefore tagging, then builds again from the tag and publishes to PyPI via OIDC trusted publishing
Version is tracked in two places
pyproject.toml(versionfield +[tool.bumpversion] current_version)token_throttle/__init__.py(__version__)
Both are updated automatically by bump-my-version. Do not edit these manually.
Development
uv sync --group dev
uv run pytest tests/unit
uv run ruff check .
tests/unit doesn't require Redis — but its default --redis-url is
redis://localhost:6379, so tests that talk to a real Redis will use one if
it's reachable there, and some of those flush the database around every test.
The suite refuses to run (aborts the whole session) against a non-empty
database unless you opt in. Point at a dedicated, empty DB index instead of a
shared one:
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 · 81 lines · 894 tokens per session scan A 8f20d8110f5b
token-throttle CLAUDE.md is an instructions file published in the GitHub repository Elijas/token-throttle (21 stars, last pushed 8d ago), licensed Apache-2.0. It adds 894 tokens to every session, about $0.0045 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
ollama AGENTS.md
AGENTS.md instructions for ollama/ollama, covering agents.md and building.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
neuron-ai CLAUDE.md
Claude Code instructions for neuron-core/neuron-ai, covering project overview, code standards, think before coding, simplicity first and surgical changes.
paperbanana copilot-instructions.md
Instructions for llmsresearch/paperbanana, covering copilot instructions for paperbanana, build & test, install for development, run full test suite and run a single test file.
MCP-Nest CLAUDE.md
Claude Code instructions for rekog-labs/MCP-Nest, covering claude.md, what this repo is, packages, layout and commands.
Albatross AGENTS.md
Instructions for morganlinton/Albatross, covering agent instructions, general and releases.