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/beaconbay/ck/claude-mdgit clone --depth 1 https://github.com/BeaconBay/ckWrote 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/beaconbay/ck/claude-md)<a href="https://agentmods.dev/instructions/beaconbay/ck/claude-md"><img src="https://agentmods.dev/badge/instructions/beaconbay/ck/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 | $0.01059 | $0.01059 |
| Opus 5 | $0.00530 | $0.00530 |
| Sonnet 5 | $0.00212 | $0.00212 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
ck 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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Development Guide
This file contains project-specific instructions for Claude and other AI agents working on the ck codebase. Whenever you actually use ck and it does something unexpected, jot it down in a file could UNEXPECTED.md - supply what you ran, what you expected to happen, what happened instead.
Release Process
Version Tagging Convention
IMPORTANT: Tags follow the format X.Y.Z (NO v prefix) to match current standard:
# Correct format (current standard since 0.3.8+)
git tag 0.4.1
git tag 0.3.9
# Old format (deprecated, do not use)
git tag v0.3.4
Always check existing tags first: git tag --sort=-version:refname
Pre-Commit Quality Checks
ALWAYS run these commands in order before any commit:
- Linting:
cargo clippy- Fix all warnings - Formatting:
cargo fmt- Format all code - Testing:
cargo test- Ensure all tests pass
Version Bump Process
All eight crates ship in lockstep. To bump from OLD to NEW:
- Workspace
Cargo.toml— update two places:[workspace.package] version = "NEW"- The seven
ck-* = { path = "...", version = "NEW", ... }lines under[workspace.dependencies]
- Update
CHANGELOG.mdwith release notes (format below) - Tag as
X.Y.Z(novprefix) —release.ymldoes the rest
That's it. Individual crate Cargo.toml files inherit the workspace version
via version.workspace = true and depend on siblings via { workspace = true }.
You do NOT need to bump package.json. The publish-npm job in
release.yml reads Cargo.toml's [workspace.package] version at publish
time and stamps package.json to match before npm publish. The committed
package.json version is informational — only the tag + Cargo.toml are
the gate.
What release.yml does on tag push
When tag X.Y.Z is pushed:
- Create GitHub release (draft) and verify tag matches
Cargo.toml - Build binaries for 5 targets (linux x86_64, macos x86_64+arm64, windows x86_64+arm64), upload as
.tar.gz/.zipassets - Publish 8 crates to crates.io in dep order, with retry-on-"already-published" and verify-via-API (User-Agent required)
- Publish to npm as
@beaconbay/ck-search— uses npm Trusted Publishing (OIDC); GitHub mints a short-lived id-token, npm validates it against the trusted-publisher config on the package, no long-lived secret. Tarball is published with SLSA provenance attestation (cryptographically tied to this workflow run + commit). The package's postinstall script downloads the platform binary from the GitHub release at user install time. - Finalize GitHub release (out of draft)
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.
- 4d ago First seen · 108 lines · 1,059 tokens per session scan A 56fb1278dc42
ck CLAUDE.md is an instructions file published in the GitHub repository BeaconBay/ck (1,717 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,059 tokens to every session, about $0.0053 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
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.
terminal-browser AGENTS.md
AGENTS.md instructions for zenbu-labs/terminal-browser, a project described as: A browser inside your terminal.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.