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/abdallahaho/ccline/claude-mdgit clone --depth 1 https://github.com/AbdallahAHO/cclineWrote 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/abdallahaho/ccline/claude-md)<a href="https://agentmods.dev/instructions/abdallahaho/ccline/claude-md"><img src="https://agentmods.dev/badge/instructions/abdallahaho/ccline/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 | $0.01926 | $0.01926 |
| Opus 5 | $0.00963 | $0.00963 |
| Sonnet 5 | $0.00385 | $0.00385 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade B, and why
ccline CLAUDE.md scanned grade B with 2 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 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.
`@abdallahaho/ccline` is a single-file bash statusline for [Claude Code](https://docs.anthropic.com/en/docs/claude-code). Install is `npx @abdallahaho/ccline@latest` — it copies one script to `~/.claude/statusline.sh` an Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **One script, no dependencies beyond the basics.** `bash`, `jq`, `curl`, `git` — nothing else. These are available everywhere Claude Code runs. How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (and humans) working on this repo.
What this is
@abdallahaho/ccline is a single-file bash statusline for Claude Code. Install is npx @abdallahaho/ccline@latest — it copies one script to ~/.claude/statusline.sh and wires a statusLine entry into ~/.claude/settings.json.
Two design constraints drive every decision in this codebase:
- It runs on every Claude Code render. Latency matters. Every subprocess spawn is a cost.
- It can be killed mid-render if it exceeds Claude Code's statusline timeout. It must never leave persistent side effects behind (stale lock files, half-written caches, etc.).
Repository layout
ccline/
├── bin/
│ ├── statusline.sh # the script — everything users actually run
│ └── install.js # npm-bin entrypoint; copies statusline.sh to ~/.claude/ and edits settings.json
├── .github/
│ └── workflows/publish.yml # release-it on push to main
├── package.json # @abdallahaho/ccline — npm package metadata + release-it config
├── README.md # user-facing docs
├── how-it-works.md # script internals — read this before touching statusline.sh
├── CHANGELOG.md # auto-generated by @release-it/conventional-changelog
├── CLAUDE.md # this file
└── LICENSE
bin/statusline.sh is the entire product. Don't factor it into multiple files — install needs to be a single cp, and shell sourcing across files adds fragility for no gain.
Design principles
- One script, no dependencies beyond the basics.
bash,jq,curl,git— nothing else. These are available everywhere Claude Code runs. - Single
jqparse. All input JSON fields are hydrated in oneevalblock (seehow-it-works.md). Don't add per-fieldjqcalls — each one is a subprocess. - Degrade quietly. Missing tool, missing field, API failure — the statusline should produce less output, never an error message and never a crash.
- Cross-platform by default. Every
date/statcall needs a BSD path and a GNU path. macOS ships BSD; Linux/WSL ships GNU; Git Bash is somewhere in between. - No persistent state. The only thing written to disk is a 60s OAuth cache under
${TMPDIR:-/tmp}/claude-${UID}/. No pidfiles, no session files. - Minimal visual noise. Badges hidden when they'd duplicate the default (e.g. permission-mode badge only renders when non-default). Don't add segments that fire on every render unless they carry signal.
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 · 137 lines · 1,926 tokens per session scan B 0247779eb436
ccline CLAUDE.md is an instructions file published in the GitHub repository AbdallahAHO/ccline (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,926 tokens to every session, about $0.0096 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
claude-hud CLAUDE.md
Instructions for jarrodwatts/claude-hud, covering claude.md, project overview, build commands, test with sample stdin data and architecture.
working-activity AGENTS.md
AGENTS.md instructions for ccch1mneyyy/working-activity, covering working-activity 项目规则, 用途, pi 版开发约定, dsh 版开发约定 and 文案.
claude-code-statusline AGENTS.md
Instructions for ilia-pluzhnikov/claude-code-statusline, covering claude-code-statusline, project shape, rules for contributors (and ai agents), editing this file and testing.
agent-tools AGENTS.md
AGENTS.md instructions for kairyou/agent-tools, covering agent instructions, build and test, layout, settled decisions and docs.
claude-code-statusline CLAUDE.md
Instructions for glauberlima/claude-code-statusline, covering claude.md, project overview, development commands, testing and run all tests (unit + integration).
claude-code-quota CLAUDE.md
Instructions for aweussom/claude-code-quota, covering claude.md — working on claude-code-quota, what this is, deployment reality (drives most of the design), traps that have already bitten us and powershell: a bom-less utf-8 .ps1 is parsed as ansi by 5.1.