ai-usagebar: Instructions file for Claude Code

CLAUDE.md

ai-usagebar CLAUDE.md is an instructions file for Claude Code, Codex from akitaonrails/ai-usagebar. It costs 4,777 tokens per session, scanned D, original, MIT.

A release guide for Claude Code that lists versioning, changelog, comparison, secret-handling, and API check requirements.

In plain words
What is it for?
Use it when preparing releases, updating Cargo and manifest versions, editing the changelog, checking tags, or running API smoke tests safely.
Why use it?
It reduces release mistakes such as mismatched versions, altered old changelog entries, exposed secrets, or unverified live API changes.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is akitaonrails/ai-usagebar's own configuration. It tells Claude Code and Codex how to work on ai-usagebar itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-usagebar configures →

Reuse

Borrowing it

Nothing to install: this file belongs to akitaonrails/ai-usagebar. 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/akitaonrails/ai-usagebar/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/akitaonrails/ai-usagebar

Made for: Claude Code, Codex.

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.

agentmods badge for ai-usagebar CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/akitaonrails/ai-usagebar/claude-md/github.svg)](https://agentmods.dev/instructions/akitaonrails/ai-usagebar/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/akitaonrails/ai-usagebar/claude-md"><img src="https://agentmods.dev/badge/instructions/akitaonrails/ai-usagebar/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.

agentmods 80×15 button for ai-usagebar CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/akitaonrails/ai-usagebar/claude-md"><img src="https://agentmods.dev/badge/instructions/akitaonrails/ai-usagebar/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,777 This file is loaded in full into every session.
When invoked 4,777 The same file — it is already loaded in full.
Security scan D 3 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04777 $0.04777
Opus 5 $0.02388 $0.02388
Sonnet 5 $0.00955 $0.00955
Haiku 4.5 $0.00478 $0.00478

Measured yesterday against content hash ebe31627c369, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade D, and why

ai-usagebar CLAUDE.md scanned grade D with 3 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 yesterday.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

the user's choice (and `chmod 600`ed by the Settings overlay), but

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

cp "$t/.SRCINFO-bin" .SRCINFO-bin && rm -rf "$t"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sLO https://github.com/akitaonrails/ai-usagebar/archive/refs/tags/vX.Y.Z.tar.gz
CLAUDE.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Notes for Claude Code (and humans) about working in this repo. Keep tight: these are invariants we keep almost-forgetting, not a project tour.

Release checklist — must do all of these

When cutting a new version (patch, minor, or major):

  1. Bump both versionsCargo.toml version and the root Omarchy manifest.json version must match the release tag.
  2. Update CHANGELOG.md:
    • Add a new ## [X.Y.Z] — YYYY-MM-DD section above the previous one.

    • Categorize entries by Added / Changed / Fixed / Security (Keep-A-Changelog).

    • Update the [Unreleased] compare link and add a new release link at the bottom.

    • Prove no published section moved, before tagging. Compare the newest released section against its own tag, byte for byte:

      prev=$(git describe --tags --abbrev=0)
      diff <(git show "$prev:CHANGELOG.md" | sed -n "/^## \[${prev#v}\]/,/^## \[/p") \
           <(sed -n "/^## \[${prev#v}\]/,/^## \[/p" CHANGELOG.md)
      

      Any output means the released section changed. It must compare, not grep for removals. The first version of this check greped ^- and therefore only caught a rewritten entry; #129 branched before v1.8.0 and its [Unreleased] bullet merged in as a pure insertion, adding a feature to a shipped release with no removed line for the grep to find. It passed clean while the section was wrong.

      make test now also enforces this without git: a guard test fails if any changelog entry appears under two versions, or if one section repeats a category heading. The manual comparison above stays because it is stronger for the newest section — the guard cannot tell a reworded entry from a new one — but the automated check is what catches a conflict resolution that quietly copies an entry into a published section, which is how it happened the third time.

      The cause is the same every time: a branch that predates the last tag carries its entries under [Unreleased], and git merges them cleanly into whatever now sits at that position — which is the section you just published. It happened to v1.6.0 (#127), to v1.8.0 (#129), and to v1.11.0 when a maintainer resolved #152's conflict with a script. A clean merge is not evidence here; the comparison is, and now the guard is too.

  3. Bump packaging/aur/PKGBUILDpkgver=X.Y.Z, pkgrel=1, reset sha256sums to 'SKIP'.
  4. Bump packaging/aur/PKGBUILD-bin — same pkgver, pkgrel=1, reset both sha256sums_x86_64 and sha256sums_aarch64 to 'SKIP'.
  5. Regenerate both .SRCINFOs NOW, before tagging — the release workflow's verify-version job rejects the tag if packaging/aur/.SRCINFO or .SRCINFO-bin still carry the old pkgver (learned at v0.17.0, which never shipped for exactly this reason):
    cd packaging/aur && makepkg --printsrcinfo > .SRCINFO
    # PKGBUILD-bin must be named PKGBUILD for makepkg — use a scratch dir:
    t=$(mktemp -d) && cp PKGBUILD-bin "$t/PKGBUILD" &&
      (cd "$t" && makepkg --printsrcinfo > .SRCINFO-bin) &&
      cp "$t/.SRCINFO-bin" .SRCINFO-bin && rm -rf "$t"
    
    The committed files keep sha256sums = SKIP; CI pins the real hashes later.
  6. Run gate before tagging:
    make test                                   # cargo test + the desktop JS gate
    cargo clippy --all-targets -- -D warnings   # clean
    cargo machete                               # no unused deps
    omarchy plugin validate .                   # plugin manifest + entry points
    
    make test rather than cargo test: it also runs the GNOME, KDE, and Omarchy frontend contract suites. If kde-plasmoid/ changed, also bump KPlugin.Version in kde-plasmoid/package/metadata.json; it is versioned independently of Cargo.toml, like the GNOME metadata.json.
  7. Commit, tag, push:
    git commit -m "vX.Y.Z — …"
    git tag -a vX.Y.Z -m "vX.Y.Z — …"
    git push origin main && git push origin vX.Y.Z
    
  8. Wait for CI (3–5 min): the tag push auto-triggers .github/workflows/release.yml which builds both x86_64 and aarch64 tarballs and publishes a GitHub Release.
  9. AUR push is automated via CI when AUR_SSH_KEY is set (since v0.4.4). The publish-aur job in .github/workflows/release.yml runs after build + release succeed, pins the real sha256s into both PKGBUILDs (steps 3-4's 'SKIP's), regenerates the .SRCINFOs, and pushes via KSXGitHub/github-actions-deploy-aur. The manual fallback below is for when the secret isn't configured or CI is unavailable.

Read the full file on GitHub · 294 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.

  1. yesterday Changed · +21 lines · +380 tokens per session ebe31627c369
  2. 3d ago Changed · +9 lines · +134 tokens per session 7937d9efdad7
  3. 11d ago First seen · 264 lines · 4,263 tokens per session scan D c677b3ff095c

Subscribe to this mod's changes

ai-usagebar CLAUDE.md is an instructions file published in the GitHub repository akitaonrails/ai-usagebar (429 stars, last pushed yesterday), licensed MIT. It adds 4,777 tokens to every session, about $0.0239 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens