later-dog
AGENTS.md2 starsChanged 29 days agoApache-2.0View on GitHub
Always use pnpm instead of npm. Node 24+ is required. Keep native backend limitations visible; fixture success does not qualify a live provider. Use cf for Cloudflare account and zone work (DNS, rules, zone settings, gateways) and Wrangler for container Workers. Change a container Worker only with a full wrangler deploy, never by patching its settings through the API. No comments in code. Say it with names, types and tests; only lines tools read (lint and test directives) and the…
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 33,315 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 repository43 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- architectSkill
- benchmark-checklistSkill
- correct-recurring-errorsSkill
- create-verification-skillSkill
- independent-reviewSkill
- maintain-verification-skillSkill
- monitor-and-shipSkill
- orchestrate-cloud-workSkill
- setup-laterdogSkill
- verify-laterdogSkill
- architectSkill
- benchmark-checklistSkill
- correct-recurring-errorsSkill
- create-verification-skillSkill
- independent-reviewSkill
- maintain-verification-skillSkill
- monitor-and-shipSkill
- orchestrate-cloud-workSkill
- setup-laterdogSkill
- verify-appSkill
- verify-laterdogSkill
- architectSkill
- benchmark-checklistSkill
- correct-recurring-errorsSkill
- create-verification-skillSkill
- independent-reviewSkill
- maintain-verification-skillSkill
- monitor-and-shipSkill
- orchestrate-cloud-workSkill
- setup-laterdogSkill
- verify-laterdogSkill
- architectSkill
- benchmark-checklistSkill
- correct-recurring-errorsSkill
- create-verification-skillSkill
- independent-reviewSkill
- maintain-verification-skillSkill
- monitor-and-shipSkill
- orchestrate-cloud-workSkill
- setup-laterdogSkill
- verify-laterdogSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 3
Always use pnpm instead of npm.
- Distinctive: line 4
Keep native backend limitations visible.
- Very specific: line 6
Use cf for Cloudflare account and zone work (DNS, rules, zone settings, gateways) and Wrangler for container Workers.
- Very specific: line 10
No comments in code. Say it with names, types and tests.
- Very specific: line 32
Before claiming a server or conversation change works, follow docs/verification/README.md.
≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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
later.dog agent notes
Always use pnpm instead of npm. Node 24+ is required. Keep native backend limitations visible; fixture success does not qualify a live provider.
Use cf for Cloudflare account and zone work (DNS, rules, zone settings, gateways) and
Wrangler for container Workers. Change a container Worker only with a full wrangler deploy,
never by patching its settings through the API.
No comments in code. Say it with names, types and tests; only lines tools read
(lint and test directives) and the licence notices adapted code came with stay.
scripts/no-comments.test.ts fails on any other; node scripts/no-comments.ts --write
removes them.
Describe later.dog on its own terms. Name another product only where later.dog works
with it (an engine it runs, an app that connects to it), never as a model to follow or a
comparison, and never cite studies, captures or reference material. That holds for code,
tests, docs, commit messages and pull requests. scripts/brand-links.test.ts keeps known
names out; the attribution the licence requires stays in NOTICE.
Work in progress, its gates, and how to resume any lane: docs/laterdog/finish-line.md. Read it before starting.
Nothing merges to main until a complete pnpm gate run (scripts/merge-gate.mjs) ends with
VERDICT: PASS on a clean checkout of the branch with the freshly fetched origin/main merged
in. The gate runs typecheck, lint, the desktop node tests, the broker tests, the packaged-server
check, the vitest suite in eight parts, and the tests in deploy/laterdog/home,
cloudflare/control-plane and deploy/laterdog/computers. A --only run is PARTIAL and never
qualifies; a test set named in LATERDOG_GATE_UNAVAILABLE stays listed on the verdict line.
Focused tests alone never qualify a merge.
Before claiming a server or conversation change works, follow
docs/verification/README.md. Always launch an
isolated fixture; never verify mutations against the user's live app or data.
The later.dog Dev app (docs/laterdog/dev-app.md) runs this
checkout, and its dogs may be editing the app they are running in. A file saved under src/
changes the person's window within a second, so keep every save working and commit working
steps. server/ and electron/ changes wait for later.dog Dev → Restart later.dog Dev; ask
the person to choose it rather than quitting or restarting the app yourself, which ends your turn.
More specific AGENTS.md files override this note within their directories.
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.

