team-guide is now positioned as the external rulebook agents read at project start: project AGENTS.md files reference team-guide rather than duplicating its content. - Delete templates/ (5 files). The only useful one — AGENTS.md skeleton — is now an inline code block in AGENTS.md §2. Handoff checklist also inlined into AGENTS.md §7. - Remove the unaudited "Product projects" section (was AGENTS.md §5). Project repos document their own release scheme in their own AGENTS.md. - Add library/ as a catalog for narrower specs. - Seed library/git-upload/SPEC.md: what to commit / what not to, .gitignore baseline, sensitive-info scan, leaked-secret recovery. - AGENTS.md gets a "How AI agents use this repo" intro and a §5 Team library section indexing library/. - README.md updated to match: explicit "for AI" framing, library section, drop product-spec mentions. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Team library
A small catalog of focused specs and reusable assets. Read the entries that match the current task; ignore the rest.
This directory is not the team's general working agreements — those
live in ../AGENTS.md. The library is for narrower,
deeper specs that would bloat AGENTS.md if inlined.
How to use this
When starting a non-trivial task:
- Read
../AGENTS.md(general rules). - Scan this catalog. If an entry matches your task, read its
SPEC.md. - If nothing matches, proceed.
Catalog
| Entry | Read it when… |
|---|---|
git-upload/ |
Pushing code to a remote, especially first push or new files |
(More entries will be added as the team encounters recurring questions worth standardizing.)
Adding to the library
Promote a topic to a library entry when all are true:
- The topic has bitten us at least twice.
- It's narrower than AGENTS.md general rules and would make AGENTS.md bloated to inline.
- Steps are stable enough to write down.
Layout for a new entry:
library/<entry-name>/
└── SPEC.md ← English, the actual spec
SPEC.md follows the same editing rules as AGENTS.md (one rule per
bullet, no emoji, examples beat prose, ~300 lines max). Lead with a
When to read this section so agents can decide quickly whether the
entry applies.
If a future entry needs scripts or skill packages, add them next to
SPEC.md. The catalog table above gets a one-line "read it when…" for
each new entry.