toktrack
AGENTS.md196 starsChanged 13 days agoMITView on GitHub
Guidance for any AI coding agent (Codex, Claude, Cursor, …) working in this repo. This file is intentionally tool-agnostic. The canonical project context lives in: Read those first. The notes below are the few things most easily missed. - Degrade gracefully on partial failure. DataLoaderService aggregates many independent sources; one source failing must never abort the whole load. Warn and continue. Optional/remote sources should fall back to their last good snapshot. A source the user selected explicitly may fail loudly,…
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 32,671 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.
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 10
Read those first. The notes below are the few things most easily missed.
- Distinctive: line 22
TDD: no implementation without a test first (RED → GREEN → REFACTOR).
- Very specific: line 37
Do not add AI/agent attribution lines (no Co-Authored-By for the agent) to commits.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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
AGENTS.md
Guidance for any AI coding agent (Codex, Claude, Cursor, …) working in this repo. This file is intentionally tool-agnostic. The canonical project context lives in:
CLAUDE.md— quick start, workflow, commands, commit rules.claude/ai-context/architecture.md— layers, paths, traits, data flow.claude/ai-context/conventions.md— naming, TDD, error handling, commits
Read those first. The notes below are the few things most easily missed.
Non-obvious rules
- Degrade gracefully on partial failure.
DataLoaderServiceaggregates many independent sources; one source failing must never abort the whole load. Warn and continue. Optional/remote sources should fall back to their last good snapshot. A source the user selected explicitly may fail loudly, but one pulled in implicitly (a configured default) must not break a plain command. See the "Data Loading" section inconventions.md. - Errors use
ToktrackError, notanyhow, in library code. - Comments and test names are English only. (Private
.dev/docs are exempt.) - TDD: no implementation without a test first (RED → GREEN → REFACTOR).
Before you finish
make check # fmt + clippy + test — must pass before committingCommits
{type}({scope}): {description}types: feat|fix|refactor|docs|test|chore|perf · scopes: parser|tui|services|cache|cli
Do not add AI/agent attribution lines (no Co-Authored-By for the agent) to commits.
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.

