What is token-throttle CLAUDE.md?

Repository instructions for releasing new versions of the token-throttle project through GitHub Actions, GitHub’s automation system. They describe version updates, testing, formatting, tagging, and publishing steps.

Use them when changing the project version or triggering a patch, minor, or major release.

They give the coding agent the project’s required release procedure and prevent local or incomplete releases.

How Elijas/token-throttle configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Elijas/token-throttle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Elijas/token-throttle/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Elijas/token-throttle

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/elijas/token-throttle/claude-md/github.svg)](https://agentmods.dev/instructions/elijas/token-throttle/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/elijas/token-throttle/claude-md"><img src="https://agentmods.dev/badge/instructions/elijas/token-throttle/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,358 This file is loaded in full into every session.

When invoked 1,358 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01358	$0.01358
Opus 5.5	$0.00543	$0.00543
Sonnet 5.5	$0.00272	$0.00272
Haiku 4.5	$0.00136	$0.00136

Measured 1mo ago against content hash 438794908f75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

CLAUDE.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 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.

Releasing is two dispatches with a reviewed PR between them. main is protected by strict required CI with no bypass, so the version bump cannot be pushed straight to main — it lands through a normal PR like any other change.

Step 1 — prepare the release PR

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

This runs CI, bumps the version, refreshes the lockfile and formatting, and opens a release/vX.Y.Z PR. Nothing is tagged or published. Review and merge that PR once required CI is green.

Step 2 — finalize after the PR merges

gh workflow run release.yml --ref main -f finalize=v0.5.1

This verifies main really carries that version, tags main's tip, and publishes to PyPI. Running it before the PR merges fails with a clear error rather than releasing anything.

What the workflow does

Prepare (-f bump=...)

Verifies the dispatch runs from refs/heads/main and that exactly one mode input is set, then runs full CI (.github/workflows/ci.yml)
Fails fast if the run is pinned to a commit that is no longer origin/main's tip
bump-my-version bump <patch|minor|major> — updates version in pyproject.toml and token_throttle/__init__.py
devtools/bump_readme_version.py — updates pip install version bounds in README.md
uv lock — syncs uv.lock with the new version
ruff check --fix, ruff format, then ruff check — applies safe lint autofixes, formats, and fails if issues remain
uv build as a gate, plus a porcelain check — fails if the tree is still dirty
Refuses to proceed if tag vX.Y.Z or branch release/vX.Y.Z already exists
Commits to release/vX.Y.Z, pushes that branch only, and opens a PR — main is never written
Explicitly dispatches ci.yml and codeql.yml onto the release branch (a branch pushed by GITHUB_TOKEN fires no push/pull_request events, so the PR would otherwise have no checks to satisfy)

Read the full file on GitHub · 114 lines

Changes

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.

1mo ago Changed · +33 lines · +464 tokens per session 438794908f75
2mo ago First seen · 81 lines · 894 tokens per session scan A 8f20d8110f5b

Subscribe to this mod's changes

token-throttle CLAUDE.md is an instructions file published in the GitHub repository Elijas/token-throttle (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,358 tokens to every session, about $0.0054 per session on Opus 5.5. 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.

Git and workflow LLM Releases ai ai-agents ai-engineering llms rate-limit

token-throttle CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
token-throttle CLAUDE.mdElijas/token-throttle	Instructions file	24	yesterday	Apache-2.0	A	1,358	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

token-throttle: Instructions file for Claude Code