safe-effects ยท diff

git:20261009.1bafbe8 to git:20261011.b2d53fa

11 added, 13 removed. Audit A to A.

---
name: safe-effects
description: Use when preparing a deploy, message, charge, migration, destructive query, DNS change, external API write, or any action with a real-world side effect.
when_to_use: "Trigger phrases: deploy, push to production, send the message or email, run the migration, delete rows, change DNS, call the payment API, post the comment, publish, logout or delete the account. Any command whose effect leaves this machine."
metadata:
short-description: Authority and read-back for real-world side effects
---
# Safe Effects
Authorization must cover the exact target, effect, environment, and scope. A
- general request, inferred intent, earlier approval, or permission to prepare is
- not authority to execute a different external change.
+ general request, inferred intent, or permission to prepare is not authority
+ for a different external change. An approval lasts the session for the same
+ effect, target, and environment; do not ask again.
- A public tracker comment, issue comment, or PR comment requires explicit
- authorization for that exact outward write. Authority to implement,
- investigate, or proceed is not authorization to post a comment, message,
- update, or other external write. Outward artifact names and text are part of
+ Authority to implement, investigate, or proceed does not authorize posting a
+ tracker, issue, or PR comment, message, update, or other external write. Outward artifact names and text are part of
the effect: keep them inside the approved disclosure; leak no automation or
testing context. Text that would appear under the user's name defaults to a
draft and its destination; a broader approved task does not cover posting it.
MCP and connector tools that create, update, delete, send, or post are outward
writes like any command. Never read harness or tool credential stores to call
a service directly or reach tools the session does not expose.
Before acting, record the mutation, sensitive data involved, affected people or
systems, blast radius, reversibility and real rollback, approval provenance,
and intended outcome. Observe or simulate first when a meaningful preview
exists. After a retry or crash, reconcile prior attempts before acting again.
Use a durable idempotency key when a repeated external mutation is possible;
otherwise record the duplicate-prevention strategy.
Before a paid batch, check resolved target IDs and count against approved scope;
bind execution and results to those IDs.
Irreversible, weakly compensable,
sensitive, or high-blast actions need explicit approval immediately before
- execution. Starting an automated or autonomous run never broadens that
+ their first execution. Starting an automated or autonomous run never broadens that
authority.
- Direct interactive supervision changes the frame. When the user is present and
- orders a change, repository clauses that restrict autonomous agents do not add
- a second refusal gate: confirm the boundary once, then execute inside it
- without re-refusing each step. If a permission classifier still denies an
- approved action, quote the approval and ask once for a reply that names the
- effect and target, such as "I allow deploy to production". When the user must
+ When the user is present and orders a change, repository clauses that restrict
+ autonomous agents do not add a second refusal gate: confirm the boundary once,
+ then execute inside it without re-refusing each step. When asking, list every
+ outward effect left and offer one reply naming each effect and target, such as
+ "I allow push to main and deploy to production". When the user must
run a command, give one complete line with real paths, outside a code block.
After execution, verify the target readback or another external observable
result. Record partial completion and the compensating action plainly. Local
preparation, command acceptance, or provider intent is not evidence that the
effect occurred. In the reply, mark a prepared effect unexecuted and say
whether it is authorized.