summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJesse Vincent <jesse@fsck.com>2026-06-10 23:34:18 -0700
committerJesse Vincent <jesse@primeradiant.com>2026-06-11 13:17:10 -0700
commit35464d67c05bd9431a1343cbd76997f45bae6a07 (patch)
tree8eacf182a85872bf322362932fb3ba2fd5a1b1bf
parent90b5433f59a7d497c98157d250a74b514e1bc13a (diff)
E27 stack: conditional impl tier + final-review tier pin + narration recipe + terse reviewer contractsdd-e27-stack
-rw-r--r--skills/subagent-driven-development/SKILL.md5
-rw-r--r--skills/subagent-driven-development/task-reviewer-prompt.md5
2 files changed, 10 insertions, 0 deletions
diff --git a/skills/subagent-driven-development/SKILL.md b/skills/subagent-driven-development/SKILL.md
index 3514a05..1945714 100644
--- a/skills/subagent-driven-development/SKILL.md
+++ b/skills/subagent-driven-development/SKILL.md
@@ -11,6 +11,9 @@ Execute plan by dispatching a fresh implementer subagent per task, a task review
**Core principle:** Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration
+**Narration:** between tool calls, narrate at most one short line — the
+ledger and the tool results carry the record.
+
**Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
## When to Use
@@ -88,6 +91,8 @@ Use the least powerful model that can handle each role to conserve cost and incr
**Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
**Architecture and design tasks**: use the most capable available model.
+The final whole-branch review is one of these — dispatch it on the most
+capable available model, not the session default.
**Review tasks**: choose the model with the same judgment, scaled to the
diff's size, complexity, and risk. A small mechanical diff does not need the
diff --git a/skills/subagent-driven-development/task-reviewer-prompt.md b/skills/subagent-driven-development/task-reviewer-prompt.md
index d2177f0..6f930e2 100644
--- a/skills/subagent-driven-development/task-reviewer-prompt.md
+++ b/skills/subagent-driven-development/task-reviewer-prompt.md
@@ -115,6 +115,11 @@ Subagent (general-purpose):
"yes." A tight report that cites lines gives the controller everything
it needs.
+ Your final message is the report itself: begin directly with the
+ spec-compliance verdict. Every line is a verdict, a finding with
+ file:line, or a check you ran — no preamble, no process narration,
+ no closing summary.
+
## Calibration
Categorize issues by actual severity. Not everything is Critical.