Propose a principle when a new decision shares its rule with decisions already listed
CI / tests (pull_request) Failing after 2m6s
CI / tests (pull_request) Failing after 2m6s
This commit is contained in:
+1
-1
@@ -10,4 +10,4 @@ paths:
|
||||
|
||||
**Every decision links to a goal or a technical principle.** An entry names the goal it serves or the technical principle under `~/.claude/principles/` it applies; one that can do neither is a missing goal, and an entry already in the repo with neither behind it is a finding. Propose the goal, never a reason of your own — `~/.claude/CLAUDE.md` → "Working loop", "Ask, don't guess" says how. An entry working against a goal or a technical principle stands only while it names the `todo.md` item that ends it.
|
||||
|
||||
**Check each new decision against the project's principles.** A principle, listed in the project's `AGENTS.md` under `## Principles`, states one rule that several decisions apply. Each time a decision is recorded, ask three things: does a principle already cover it, does it break one, does it suggest a new one? A decision a principle covers adds no title to `AGENTS.md`. A break, a new principle, or a change to one is the human's: ask, unless the evidence is overwhelming, and leave the principles as they are until the human answers. A break questions both sides: either the principle or the decision is wrong.
|
||||
**Check each new decision against the project's principles.** A principle, listed in the project's `AGENTS.md` under `## Principles`, states one rule that several decisions apply. Each time a decision is recorded, ask three things: does a principle already cover it, does it break one, does it apply the same rule as decisions already listed? A decision a principle covers adds no title to `AGENTS.md`. A rule it shares with listed decisions is a new principle, which covers them too: once the human approves it, their titles leave `AGENTS.md`, so a project distils its principles as its decisions land. A break, a new principle, or a change to one is the human's: ask, unless the evidence is overwhelming, and leave the principles as they are until the human answers. A break questions both sides: either the principle or the decision is wrong.
|
||||
|
||||
Reference in New Issue
Block a user