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/oleksbard/cosmobar/claude-mdgit clone --depth 1 https://github.com/oleksbard/cosmobarWrote 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/oleksbard/cosmobar/claude-md)<a href="https://agentmods.dev/instructions/oleksbard/cosmobar/claude-md"><img src="https://agentmods.dev/badge/instructions/oleksbard/cosmobar/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 5.1 | $0.01743 | $0.01743 |
| Opus 5 | $0.00872 | $0.00872 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade B, and why
cosmobar CLAUDE.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
make dev # build + wire ./testsettings/.claude/settings.json for live testing How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
cosmobar is a single static Go binary that renders the Claude Code status line. Claude Code invokes it once per refresh, piping a session JSON blob to stdin; cosmobar prints one-or-more terminal rows to stdout. No runtime deps, no jq, no Nerd Font — the only module dependency is BurntSushi/toml.
Commands
make build # go build -o ./bin/cosmobar .
make test # go test ./...
make fmt # go fmt ./...
go test ./internal/render # test one package
go test ./internal/segments -run TestCatalogMatchesRegistry # one test
go vet ./... # must pass; CI runs it
go run . preview --cols 80 # fast visual loop without building
make dev # build + wire ./testsettings/.claude/settings.json for live testing
Never point the Claude Code statusLine command at go run . — it recompiles every refresh. Always use a built binary.
Architecture
Render pipeline (the spine). internal/cli/cmd_print.go:renderFromJSON is the testable core: it parses stdin (session.Parse), loads TOML config (config.Load/config.DefaultPath), detects the terminal render.Profile, does one git call (cached per session ~1s in the OS temp dir via git.Lookup; everything else comes from the stdin JSON), and hands everything to statusline.Render as a fully-injected statusline.Input (Git, Cols, Profile, Now are all passed in, so the render is deterministic and unit-testable). cosmobar preview (internal/cli/cmd_preview.go) reuses this exact same pipeline with mocked session/git data — preview output is guaranteed to match the live line.
Segments are a self-registering plugin registry. Each segment lives in internal/segments/<name>.go, implements Renderer (Name() + Render(ctx *Context) (Segment, bool) where ok=false hides it), and calls register(...) in an init(). statusline.Render walks config.Order, looks each name up via segments.Get, and collects the shown segments. To add a segment: create the file, register it, add a matching entry to the catalog in catalog.go, and add a table test.
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 · 53 lines · 1,743 tokens per session scan B 76d6734ea709
cosmobar CLAUDE.md is an instructions file published in the GitHub repository oleksbard/cosmobar (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,743 tokens to every session, about $0.0087 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
sentry-instrumentation AGENTS.md
Instructions for tortastudios/sentry-instrumentation, covering agents guide — sentry-instrumentation, what this repo is, this repo has no "skill registry", if you're a codex agent asked to install this skill and skill-enable block (copy into consumer agents.md).
critical-thinking AGENTS.md
Instructions for Johna2an/critical-thinking, covering agents.md, repo map, install (for a user asking "should i install this?"), working in this repo and running an eval round.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
hometax-doum AGENTS.md
AGENTS.md instructions for lbiz-partners/hometax-doum, covering claude.md — hometax-doum 개발 규칙 (하네스와 쌍), 규칙 ↔ 강제 장치 and 운용 메모.
powerglide AGENTS.md
Instructions for bkataru/powerglide, covering powerglide agent protocol & integration guide, the ralph loop protocol, termination signals, velocity control and reliable pty execution.