Skip to content

fix: the doc boundary is on-demand, not off-limits #73

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jothimani-rajendran merged 1 commit into from
Sep 13, 2026
Merged

fix: the doc boundary is on-demand, not off-limits #73

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions AGENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,14 @@ source_of_truth: AGENTS.md; adapters: thin_wrappers(delegate_here); authority: n

## Data boundaries

- never_read(file: README.md)
- never_read(path: docs/)
These are a context-economy rule, not a secrecy one. `README.md` and `docs/` are large,
human-facing, and irrelevant to most tasks, so loading them by default spends context an
agent needs for the actual work. They are **on-demand, not off-limits**: when the task is to
change one of them, read it and change it.

- read_on_demand(file: README.md) — not read for general work; read and edit it when the task
is to change it
- read_on_demand(path: docs/) — same
- agent_source: AGENTS.md, .agents/skills/<id>/SKILL.md, .agents/policies/<id>/manifest.yaml
- human_source: docs/**

Expand Down