Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sainteye/clawdlinenpx agentmods add skills/sainteye/clawdline/progressWrote 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/skills/sainteye/clawdline/progress)<a href="https://agentmods.dev/skills/sainteye/clawdline/progress"><img src="https://agentmods.dev/badge/skills/sainteye/clawdline/progress/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/skills/sainteye/clawdline/progress"><img src="https://agentmods.dev/badge/skills/sainteye/clawdline/progress.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 | $0.00277 | $0.01338 |
| Opus 5 | $0.00138 | $0.00669 |
| Sonnet 5 | $0.00055 | $0.00268 |
| Haiku 4.5 | $0.00028 | $0.00134 |
Grade A, and why
progress 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 3d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Progress, for a run somebody is waiting on
What the reader gets. A long command normally says nothing until it is over, and the person who started it is either sitting in front of that terminal or has no idea. This writes one small file while the run happens, and Clawdline's bar and claude-bestiary's terminal status line draw it: what is running, in which tree, since when, which phase it is in, and — when a measurement exists — how far through it is. The person watching from a phone stops having to guess how much longer.
It is not specific to tests or builds. label and phase are free text, so a lint run, a data
import, a migration and a video encode all fit the same record.
The one line
clawdline-progress run --label lint --typical 120 -- ./scripts/lint.sh
Reach for this form. The helper is the parent process, so the exit status is its own and the signals are its own: it exits on the command's own status, and a run that is killed is written down as killed. You install no traps and cannot get them wrong.
--labelis what a person reads. Two or three words, the thing being done:lint,import,staging deploy. With none, the command's own file name is used.--typical <seconds>is optional, and only for a duration somebody has actually measured. It is what turns the bar from elapsed time into a proportion. With no measurement, pass nothing: the field is then absent rather than invented, which is the whole point — to a reader an invented number is indistinguishable from a measured one../build.shin this repository passes none for exactly that reason.--stale-after <seconds>(default 900) is when a reader should stop believing arunningrow whose writer has stopped.--log <path>names a log worth opening.
Where the file is, in order: $CLAWDLINE_PROGRESS if it is set; otherwise
/Applications/Clawdline.app/Contents/Resources/clawdline-progress.sh; otherwise the same path
under $HOME/Applications; otherwise, inside a checkout of this repository,
Resources/clawdline-progress.sh.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 103 lines · 277 tokens per session scan A b1f6b1281d02
progress is a skill published in the GitHub repository sainteye/clawdline (1 stars, last pushed 4d ago), licensed MIT. It adds 277 tokens to every session and 1,338 once invoked, about $0.0014 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 2026-09-08.
Other skills, from other repositories
cctop-setup
Use when cctop-hook command fails or is not found. Guides user to install the cctop menubar app.
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
onlyswitch-deeplink
Invoke OnlySwitch built-in switches or buttons via deeplink. Use when the user asks to toggle or trigger an OnlySwitch action (e.g. empty trash, keep awake, dark mode, mute, hide desktop, clear clipboard, eject discs, Xcode derived data, and any other built-in switch or button). Resolve the request to the correct…
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
notifications
Send notifications through the unified notification router.
outlook
Manage Outlook email — drafting, sending, organizing, rules, vacation replies, and inbox analysis.