From 40b16b87963b085817bfb82c26eef7d0408fa8a5 Mon Sep 17 00:00:00 2001 From: alexion Date: Sat, 1 Aug 2026 18:19:32 -0400 Subject: [PATCH] fix(skills): require isolated review and test workers --- skills/review/SKILL.md | 4 ++-- skills/subagents/SKILL.md | 4 ++-- skills/test-driven-development/SKILL.md | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/skills/review/SKILL.md b/skills/review/SKILL.md index 68f89e4..d373dbe 100644 --- a/skills/review/SKILL.md +++ b/skills/review/SKILL.md @@ -32,8 +32,8 @@ Done when the chosen change set is explicit and reviewers have enough input to j Run independent dimension reviewers through whatever real context boundary the current harness provides. A separate agent, worker, subprocess, or documented headless session is sufficient when each reviewer can inspect its dimension without seeing the parent review's intermediate conclusions. Use one reviewer per dimension when practical. -If no real context boundary is available, state that limitation before reviewing. -Proceed in-process only as an explicitly degraded fallback, and preserve separate report sections. +If no real context boundary is available, stop before reviewing and report that independent review cannot be completed in the current runtime. +Do not replace independent reviewers with in-process role switches. Use these reviewer files: diff --git a/skills/subagents/SKILL.md b/skills/subagents/SKILL.md index 3ad059d..d2f11eb 100644 --- a/skills/subagents/SKILL.md +++ b/skills/subagents/SKILL.md @@ -13,9 +13,9 @@ The supported tool names are `subagent_spawn`, `subagent_batch`, `subagent_list` If these tools are unavailable, do not pretend that an in-process role switch is a subagent. State that Pi subagent tools are unavailable in the current runtime. -Do not perform the delegated subagent work in-process unless the caller explicitly permits a degraded fallback. +Do not perform the delegated subagent work in-process. -Done when the run has either a supported subagent tool path or a caller-approved degraded mode. +Done when the run has a supported subagent tool path. ## 2. Prepare a bounded prompt diff --git a/skills/test-driven-development/SKILL.md b/skills/test-driven-development/SKILL.md index cac949a..b1cf2a3 100644 --- a/skills/test-driven-development/SKILL.md +++ b/skills/test-driven-development/SKILL.md @@ -17,8 +17,8 @@ Tests are always written by someone other than the agent doing implementation. Launch an independent test writer through whatever real context boundary the current harness provides. A separate agent, worker, subprocess, or documented headless session is sufficient when it cannot see the implementation agent's private backlog. -If no real context boundary is available, state that limitation before writing tests. -Proceed in-process only as an explicitly degraded fallback, and preserve role separation as much as possible. +If no real context boundary is available, stop before writing tests and report that test-driven development cannot be completed in the current runtime. +Do not replace the independent test writer with an in-process role switch. Do not silently skip the independent-test-writer requirement. The implementation agent may keep a private behavior backlog.