summer-solstice
AGENTS.md0 starsChanged 46 days agoMITView on GitHub
This is the public Summer Solstice plugin: a generic product factory. It must never contain live intel. - No live intel here. No product names, slugs, or domains of products in flight, no competitor names in live use, no records, no event files, no workspace config, no account IDs, and no secrets. Tests and fixtures use synthetic data only, and every file under cli/tests/fixtures/ carries the marker solstice-fixture: synthetic. Build secret-shaped test strings at runtime. - Knowledge work about live…
- Commits and pushes
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.
In this repository9 other files it gives its agents.
- build-handoffSkill
- compounding-logSkill
- demand-confidence-gateSkill
- grow-sell-killSkill
- launch-distributionSkill
- opportunity-scoringSkill
- opportunity-sourcingSkill
- positioning-teardownSkill
- seed-market-selectionSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 1 is common, 0 are distinctive, and 1 is very specific to this project.
≈1
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
- Common: line 6
No live intel here: No product names, slugs, or domains of products in flight, no competitor names in live use, no records, no event files, …
- Very specific: line 28
Run the CLI tests with cd cli && uv run pytest -q.
≈ “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
Agent rules for this repo
This is the public Summer Solstice plugin: a generic product factory. It must never contain live intel.
- No live intel here. No product names, slugs, or domains of products in
flight, no competitor names in live use, no records, no event files, no
workspace config, no account IDs, and no secrets. Tests and fixtures use
synthetic data only, and every file under
cli/tests/fixtures/carries the markersolstice-fixture: synthetic. Build secret-shaped test strings at runtime. - Knowledge work about live products runs from the private workspace
checkout, not this one.
ce-plan,ce-compound, and similar work about a real product write into the workspace's owndocs_root. In this checkout, compound-engineering writes to.ce-artifacts/, which is gitignored and must stay untracked. - Never run
git push --no-verifyon this repo. The pre-push hook in.githooks/pre-pushscans every pushed commit (contents, paths, and messages) against the private denylist and secret patterns, and it fails closed. If it blocks a push, remove the leak from the commits; do not bypass it. - Confirm the hook is armed with
solstice doctor(thepre-push hookline must beok). Arm it withsolstice hooks install <this checkout> --workspace <private workspace>. - v1 skills under
skills/stay untouched until they are removed in the v2 release.
Run the CLI tests with cd cli && uv run pytest -q.
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.

