For coding agents

Get going

Before enlightenment: chop wood, carry water.

Do not invent policy from the blog. Install a thin working relationship, understand two fail-closed boundaries, prove one real task — then stop.

Six steps

1

Take the pack

Unzip codex-hour-starter.zip or browse packs/codex-hour/.
2

Drop AGENTS.md and .agents/ into the project

Project-local. Start a new Codex task so guidance and skills load from the beginning.
3

Rename the skill

Change example-domain-task triggers and proof to the human’s real weekly job.
4

Keep two fail-closed boundaries

No secrets in chat; no consequential write without a visible human decision. Keep Codex project guidance, host sandbox/permissions, and the decision point as separate layers.
5

Sign off one pattern

One signed-off row with a real failure line in patterns/WORKING-PATTERNS.md.
6

Freeze a clock + run one task

Set harness.start to today. Run the skill with its proof checklist — not a plan alone.

Prefer skills/rules/patterns on disk over chat folklore.
Fail closed on secrets and irreversible outbound. Capture via desktop dialog into Bitwarden (Password Manager for humans; Bitwarden Secrets Manager for agent tokens) — never into chat.
Prefer trash over hard delete — move files to OS/project trash so mistakes stay recoverable (signed pattern, not a third always-on P0).
File blog sparks in the repo’s blog-inbox.md — do not publish the inbox. Promote at EOW or skip.
Keep portable procedure in Agent Skills, repository expectations in AGENTS.md, and host enforcement in Codex sandboxing/permissions.
Worktrees isolate state; they do not replace one-writer ownership, explicit handoffs, or proof.
Do not use model turns as background sensors. One explicitly requested diagnostic gets one bounded evidence pass; reviews stay read-only.
Public shape is locked at v1.2 — see BASELINE-v1.2.md.

Markdown twin for clones: AGENTS.md · Site home: chopwoodcarrywater.uk