The record of every run agents made on this project — what was asked, where the work went, how it ended, what the agent said — where it lives, how to read it, and when to look back before you work.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Every run an agent made on this project leaves a record on the branch agent-data, never on a code branch; your checkout does not contain it. A run is two files under agents/<who>/: the card, <id>.json — what was asked, the branch, the pull request, how it ended, what it cost — and the diary, <id>.jsonl — what the agent said along the way, its result.
Read them with the logs command, always run by its full name: npx @openagt/skill-logs@0.1. You only read: the program that ran an agent records its run, at its end. The command's delete and patch, and its --local and --full flags, are for the dashboard that shows the runs; never use them. A refusal exits 1 with a line on stderr; a wrong command line exits 2 with the usage.
npx @openagt/skill-logs@0.1 [--branch <name>] [--limit N]
the runs, newest first, as one JSON array of cards — the newest 20
unless --limit says otherwise; --branch keeps the runs on one branch
npx @openagt/skill-logs@0.1 show <id> one run: its card, plus `diary`, the lines of what the agent
said, its result, how it ended, and what it cost
A ticket may have been worked before. Claiming it names who claimed it before you: a run's id, shaped like 2026-09-08T18-14-30-111Z, read with npx @openagt/skill-logs@0.1 show <id>, or else a branch, read with npx @openagt/skill-logs@0.1 --branch <name>; no run on that branch means no record: read the branch itself. A stopped or failed run tells you what to avoid: read what its agent said before it ended. A done run with a pr means the work may already be there: read the pull request before doing it again.
{
"id": "2026-09-08T18-14-30-111Z",
"startedAt": "2026-09-08T18:14:30.651Z",
"endedAt": "2026-09-08T18:15:40.433Z",
"status": "done",
"intent": "what the agent was asked to do",
"driver": "claude-code",
"model": "opus",
"branch": "agent-2026-09-08T18-14-30-111Z",
"pr": { "number": 1765, "url": "https://example.com/org/repo/pull/1765" },
"cost": 0.62
}
status is running, done, stopped, failed or waiting (ended on a question the agent asked, until it is answered). cost is in US dollars. Every field but id, startedAt and status is absent when unknown. The program that wrote the card may keep its own bookkeeping under one more key, caller; the command never prints it to you.
One JSON object per line. Four kinds are the agent's, in the order they happened:
{"kind":"said","text":"…"} something the agent said
{"kind":"result","text":"…"} the agent's final answer for a turn
{"kind":"cost","usd":0.62} what a stretch of the run cost, in US dollars
{"kind":"ended","status":"failed","detail":"…"} how the run ended; detail when it did not end well
Each line may also carry at, the time it was written, in the card's format.
Any other kind of line is the writing program's own; show leaves it out.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Where your work goes (a branch named agent-<name>), how to name it, what must be true before you finish, and how to push it when you are asked to.
The English summary is being prepared. Showing the original description.
A real browser you drive from the shell, to see or act on a web page (open it, read it, click, type, take a screenshot), such as checking that the app you changed works.
The English summary is being prepared. Showing the original description.
Post a message to the team's Discord channel from the shell, when a task asks you to tell people something there.
The English summary is being prepared. Showing the original description.
The project's git host is GitHub: how to open your pull request when you are asked to, how to land it, and how to read and close the project's issues.
The English summary is being prepared. Showing the original description.
Refactor a part of the code to make it as maintainable as possible.
The English summary is being prepared. Showing the original description.
Find the parts of the code that need refactoring and put their maintainability and security work on the agent queue. Queues only.
The English summary is being prepared. Showing the original description.