spacedock
AGENTS.md85 starsChanged 5 months agoApache-2.0View on GitHub
This repo builds the Go-based spacedock launcher and the project-side skill integration behind its stable command surface. Run these before claiming work is complete: Add focused tests for each stage before implementing that stage. Cut stable releases from main via an annotated vX.Y.Z tag — see docs/releasing.md. next is a dev-only source-build convenience branch (go install …@next, --plugin-dir) — the edge marketplace entry resolves main directly, so next is not a re-pull source for any installer. Do not cut a…
- Installs packages
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 31,774 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 repository13 other files it gives its agents.
- commissionSkill
- compassSkill
- debriefSkill
- ensignSkill
- feedback-rejection-flowSkill
- first-officerSkill
- fo-dispatch-recoverySkill
- fo-gate-lifecycleSkill
- fo-status-viewerSkill
- present-gateSkill
- refitSkill
- reviewSkill
- surveySkill
The file
We split this AGENTS.md into the rules it gives an agent
9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
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 7
Prefer small Go packages with clear boundaries.
- Distinctive: line 8
Use the standard library unless a dependency removes real complexity.
- Distinctive: line 9
Keep command output stable and test it with fixtures.
- Distinctive: line 13
Run these before claiming work is complete:
- Distinctive: line 21
Add focused tests for each stage before implementing that stage.
- Distinctive: line 41
Keep skill instructions declarative.
- Distinctive: line 42
Add skill smoke tests before changing first-officer or ensign command text.
- Very specific: line 47
When adding a new runtime host or debugging first-contact runtime friction, read docs/runtime-support.md first.
- Distinctive: line 48
Use the documented "assume it already works" operating prompt before declaring a host impossible due to auth setup, extension/package …
≈ “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
Agent Instructions
This repo builds the Go-based spacedock launcher and the project-side skill integration behind its stable command surface.
Priorities
- Prefer small Go packages with clear boundaries. Avoid a single large CLI file.
- Use the standard library unless a dependency removes real complexity.
- Keep command output stable and test it with fixtures.
Expected Commands
Run these before claiming work is complete:
go test ./...
go test ./... -race
gofmt -w ./cmd ./internalAdd focused tests for each stage before implementing that stage.
Releasing
Cut stable releases from main via an annotated vX.Y.Z tag — see docs/releasing.md. next is a dev-only source-build convenience branch (go install …@next, --plugin-dir) — the edge marketplace entry resolves main directly, so next is not a re-pull source for any installer. Do not cut a stable vX.Y.Z tag from it.
Project Shape
cmd/spacedock/: process entry point only.internal/cli/: command routing, usage text, exit-code behavior.internal/status/: status implementation.docs/specs/: design contracts, including the state behavior extension.docs/roadmap/: bootstrap and migration roadmap.docs/dev/README.md: development workflow definition.docs/dev/.spacedock-state/: development workflow entities in a separate state checkout.skills/: first-officer, ensign, and satellite skills plus integration fixtures.
Skill Development
- Skills should call
spacedock, not plugin-private script paths. - Keep skill instructions declarative. Let the binary own path resolution and mutation guards.
- Add skill smoke tests before changing first-officer or ensign command text.
- Preserve current FO/ensign write-scope rules: the first officer mutates entity state; ensigns write assigned code, reports, and artifacts.
Runtime Support
- When adding a new runtime host or debugging first-contact runtime friction, read
docs/runtime-support.mdfirst. - Use the documented "assume it already works" operating prompt before declaring a host impossible due to auth setup, extension/package discovery, or tool-shape mismatch.
- Prove runtime claims with live or fixture-backed durable state evidence - see
docs/runtime-support.md.
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.