Borrowing it
Nothing to install: this file belongs to mryll/claudebar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mryll/claudebar/master/CLAUDE.mdgit clone --depth 1 https://github.com/mryll/claudebarWrote 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/mryll/claudebar/claude-md)<a href="https://agentmods.dev/instructions/mryll/claudebar/claude-md"><img src="https://agentmods.dev/badge/instructions/mryll/claudebar/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.
<a href="https://agentmods.dev/instructions/mryll/claudebar/claude-md"><img src="https://agentmods.dev/badge/instructions/mryll/claudebar/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00790 | $0.00790 |
| Opus 5.5 | $0.00316 | $0.00316 |
| Sonnet 5.5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
claudebar CLAUDE.md scanned grade A 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 22d 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- Secrets never go in argv NOR in a child's environment — stdin for curl (`--config -`, `--data @-`), stdin or a pipe for jq (`b64_lines`; `--rawfile x <(...)` when stdin already carries the document). The same goes for Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Install: `make install PREFIX=~/.local` (or `sudo make install`); no build step Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Every `curl` starts with `-q` as the FIRST argument. `curl_auth_cfg` is the only place a curl config is built, and it REJECTS tokens that could inject config lines. How it starts
The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
- Install:
make install PREFIX=~/.local(orsudo make install); no build step - Tests:
bash tests/run_all.sh
Non-Obvious Rules
- The script must always exit 0 with valid Waybar JSON (
{"text","tooltip","class"}), even on errors — Waybar hides modules that exit non-zero. Usedie(). Tooltip and bar text are Pango markup. - The CLI always runs through
/bin/sh -c 'exec "$0" "$@"', never direct. A nonexistent binary handed to Quickshell 0.3.1 can abort the whole shell inside the failed start (#6), before any QML signal fires. The failed-start discriminator is!sawExit || exitCode === 126 || exitCode === 127on empty output; any other exited-empty run is an operational failure, never "not installed". - The bundled-script fallback fires ONLY on a failed start. PATH first, always: the AUR release wins when it exists. Never fall back on operational errors.
schema_versionis pinned to 2 on both sides. A schema bump must change script, panel and tests in one commit.installCmdis the one constant — the message shows it and the button copies it (argv-exec, no shell line). The button gates onnotInstalled, never on error text.- A tooltip meter is PARKED, not rendered in place: a
METER:<i>sentinel plus parallelmeter_*arrays, resolved by the width pass — which must skipMETER:lines or the measurement is circular. All meters in one tooltip share the same bar length. After mutatingBAR_LEN, rebuildGRAD_CELLS(GRAD_CELLS=(); init_grad_cells) — indexing past it is fatal underset -u.
Hardening invariants
The plugin runs inside the long-lived omarchy-shell process, so a blocking read
or write takes the whole shell down. Regression tests live in
tests/test_hardening.sh; the rationale for each rule is in the script's own
comments at the relevant site.
- Every read of a file this script does not own goes through
read_bounded(O_NONBLOCK open + byte cap);jqnever opens a foreign path itself. - Every write on a predictable path is guarded, on the fd where one exists. The credentials write-back stages its temp in the SAME directory as the target (rename(2), atomic), creates it BEFORE the refresh POST (a 200 may rotate the refresh token), and re-reads + compares before the
mv(the claude CLI also writes that file). - Every
curlstarts with-qas the FIRST argument.curl_auth_cfgis the only place a curl config is built, and it REJECTS tokens that could inject config lines. - Secrets never go in argv NOR in a child's environment — stdin for curl (
--config -,--data @-), stdin or a pipe for jq (b64_lines;--rawfile x <(...)when stdin already carries the document). The same goes for billing amounts (spend, limit, prepaid balance) and everything that may carry them —extra_usage,max_pctandlast_errorin--json, the bar text and the tooltip. Free text goes throughb64_lines, since jq 1.7's raw input mangles UTF-8 split across its 4 KiB read blocks. - The panel refuses to retain more than 1Mi UTF-16 units of CLI output (a tripwire with a per-run flag, not a limit).
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.
- 22d ago Changed · +106 tokens per session 1299a0606b25
- 2mo ago Changed · -72 lines · -1,350 tokens per session ecd975cdc2d2
- 2mo ago First seen · 99 lines · 2,034 tokens per session scan A 47ebb13e8afd
claudebar CLAUDE.md is an instructions file published in the GitHub repository mryll/claudebar (63 stars, last pushed yesterday), licensed MIT. It adds 790 tokens to every session, about $0.0032 per session on Opus 5.5. A static security scan graded it A with 3 findings (sends data to an external url, asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
claudebar CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claudebar CLAUDE.mdmryll/claudebar | Instructions file | 63 | yesterday | MIT | A | 790 | 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 |