ADD
AGENTS.md19 starsChanged 38 days agoMITView on GitHub
This project uses ADD (AI-Driven Development): the AI plans, builds and verifies; the human owns direction and reviews the result. There is no CLI. The method is one skill file (.claude/skills/add/SKILL.md), run with files, git and the project's own test command. Orient first, every session: read .add/PROJECT.md (goal:, invariants:, test_cmd:), then the open task and milestone files under .add/tasks/ and .add/milestones/ (any status: that is not done or dropped), and the last few commits. Resume an open task; otherwise size…
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.
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 8
Orient first, every session: read .add/PROJECT.md (goal:, invariants:, test_cmd:), then the open task and milestone files under .add/tasks/ …
≈ “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
<!-- ADD:BEGIN — managed by the ADD installer; do not edit inside -->ADD — how to work in this repo
This project uses ADD (AI-Driven Development): the AI plans, builds and verifies; the human
owns direction and reviews the result. There is no CLI. The method is one skill file
(.claude/skills/add/SKILL.md), run with files, git and the project's own test command.
Orient first, every session: read .add/PROJECT.md (goal:, invariants:, test_cmd:),
then the open task and milestone files under .add/tasks/ and .add/milestones/ (any status:
that is not done or dropped), and the last few commits. Resume an open task; otherwise size
the work.
Size the work. You route and go; the human reviews after.
| the request | lane | what persists |
| mechanical, or a small behavior: ≤3 adjacent files, one sitting, no unknowns | Quick | a red→green test + one commit |
| one behavior worth a written contract | Task | .add/tasks/<slug>.md + its commits |
| the answer IS the deliverable: investigate · evaluate · research | Explore | the task's ## FINDINGS |
| a theme, or more than one task | Milestone | .add/milestones/<slug>.md + its tasks |
Floor: anything touching security · data · architecture, or a surface other code consumes, is at least a Task. When in doubt, size up.
Then follow the skill: Direction (rules · assumptions · failing checks, sealed by a
freeze(<slug>) commit) → Build (to green, sealed files untouched) → Verify (seal intact · fresh
green run · residue review · verdict in ## EVIDENCE, committed as verify(<slug>): <verdict>).
Rules that bind: the invariants: in PROJECT.md hold for every change, Quick included. Never
weaken a sealed check or edit the contract to get green; changed intent is a visible
refreeze(<slug>) commit. A security finding is a HARD-STOP verdict, flagged at the top of the
report.
Book: https://pilotspace.github.io/ADD/. Edit outside the markers.
<!-- ADD:END -->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.