agent-log-gif
AGENTS.md9 starsChanged 8 months agoApache-2.0View on GitHub
Uses uv. Run tests: Run the tool: uv run agent-log-gif json tests/sample_session.jsonl -o tmp/test.gif Lint and format (also runs via git hook): All commands: just --list Practice TDD: failing test first, then implementation. Bundle test + code + docs in one commit. Put generated output for review (GIFs, MP4s, renders) in the repo's tmp/ dir (gitignored). A repo-relative path works everywhere: it resolves to /workspace/tmp in the devcontainer and tmp/ under the repo on a native checkout. Web UI (web/):…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- lucide-iconSkill
- visual-proofSkill
- worktree-setupSkill
- agent-log-gifSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Put generated output for review (GIFs, MP4s, renders) in the repo's tmp/ dir (gitignored).
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Uses uv. Run tests:
just testRun the tool:
uv run agent-log-gif json tests/sample_session.jsonl -o tmp/test.gifLint and format (also runs via git hook):
just lintAll commands: just --list
Practice TDD: failing test first, then implementation. Bundle test + code + docs in one commit.
Put generated output for review (GIFs, MP4s, renders) in the repo's tmp/ dir (gitignored). A repo-relative path works everywhere: it resolves to /workspace/tmp in the devcontainer and tmp/ under the repo on a native checkout.
Web UI (web/): use the agent-browser skill to verify the frontend visually, and write Playwright e2e tests for it. Use bun for any JS dependency/build tooling (not npm/yarn/pnpm); check before installing Playwright or other tools.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.