An agentic skills framework & software development methodology that works.
E27 stack: conditional impl tier + final-review tier pin + narration recipe + terse reviewer contract
Jesse Vincente97faafb5a9f
diff --git a/skills/subagent-driven-development/SKILL.md b/skills/subagent-driven-development/SKILL.mdindex 3514a05e2..1945714af 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 thediff's size, complexity, and risk. A small mechanical diff does not need thediff --git a/skills/subagent-driven-development/task-reviewer-prompt.md b/skills/subagent-driven-development/task-reviewer-prompt.mdindex d2177f0f5..6f930e279 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 everythingit 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.+## CalibrationCategorize issues by actual severity. Not everything is Critical.