agent-progress SKILL.md skillA
agent-progress from csinva/agent-progress is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add csinva/agent-progress/agent-progress@git:20260924.3f59ce5Pins git:20260924.3f59ce5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- csinva/agent-progress
- Path
skills/agent-progress/SKILL.md- Versions recorded
- 7
- Latest version
- git:20260924.3f59ce5, committed Sep 24, 2026
- First version recorded
- Sep 8, 2026
- Size
- 21,259 bytes
- Repository stars
- 3
- License
- MIT
Run and track any long-running job with a progress bar in the Claude Code statusline - training runs, evals, sweeps, data pipelines, test suites, builds, migrations, downloads, simulations, backups. Use whenever the user asks for something slow to be started, in whatever words - "run training", "start the eval", "kick off the sweep", "retrain the model", "run the pipeline", "run this in the background" - and whenever they ask about one already going: "how long will this take…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Progress bars for long-running jobs `agent-progress` puts a live bar in the user's statusline for any job that takes minutes to days. Your involvement is almost entirely **up front**: 1. Decide **how this particular job's progress can be observed**. 2. Give a rough estimate of how long it will take - on the command line, as `AGENT_PROGRESS_ETA=<duration>` in front of a plain command, or `--eta` for `agent-progress run`. A bar without one shows `?` for the time remaining. 3. Launch it. After that a background watcher does the work. It re-observes the job on a slow cadence, recomputes the total estimate from what it sees, and marks the job done or failed with the real exit code. **Do not poll the job yourself** — no loops, no repeated `ls`, no waiting. Check in only when you have a reason to. Use `agent-progress`. If that is not found, use `~/.local/bin/agent-progress` (the installer puts it there, and it works by full path whether or not that directory is on PATH); failing that, `python3` on the plugin's `scripts/agent_progress.py`. `agent-progress autotrack '<command>'` shows whether a given command would be caught automatically, and why. …
Read the whole file at its exact version.
How to install
mdr add csinva/agent-progress/agent-progress@sha256:2bcc51371d5bc00bThe line at the top of this page pins the label git:20260924.3f59ce5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_a2lbz2zw5jrnu7ua)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 8, 2026 and Sep 24, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260924.3f59ce5 latest | 2026-09-24 | 3f59ce5 | 21,259 B | A | view · diff |
| git:20260924.bc910b3 | 2026-09-24 | bc910b3 | 20,140 B | A | view · diff |
| git:20260914.920c309 | 2026-09-14 | 920c309 | 20,015 B | A | view · diff |
| git:20260909.0b750d2 | 2026-09-09 | 0b750d2 | 19,568 B | A | view · diff |
| git:20260909.3f3d5ed | 2026-09-09 | 3f3d5ed | 19,388 B | A | view · diff |
| git:20260908.b10d84d | 2026-09-08 | b10d84d | 18,618 B | A | view · diff |
| git:20260908.723d46d | 2026-09-08 | 723d46d | 18,489 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (21259 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
csinva/agent-progress · 3 stars · license MIT · pushed 2026-09-26 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_a2lbz2zw5jrnu7ua GET https://markdownregistry.com/api/v1/resolve?ref=csinva/agent-progress/agent-progress GET https://markdownregistry.com/api/v1/blob/2bcc51371d5bc00b0e2a8a770833113f316e58955b2b553d0e38640c7e0e67b4
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.