Compare commits

..

1 Commits

Author SHA1 Message Date
Drew Ritter
fa07663322 fix(skills): plans reference the spec instead of restating it (SUP-333 #1)
writing-plans told agents to "document everything they need to know"
assuming zero context — every agent in the 2026-06-09 six-agent quorum
sweep obeyed and restated the entire spec inline in the plan
(cost-spec-plan-duplication failed 5/5 completed agents; pi's plan was
683 lines of duplicated spec).

- writing-plans: state the division of labor — spec owns WHAT/WHY,
  plan owns HOW; cite the spec by path/section, never restate it.
  "Zero context" means mechanically executable steps, not duplication.
  Add a **Spec:** line to the plan header template.
- brainstorming: close the path loophole the re-run exposed — claude
  shortened docs/superpowers/specs/ to docs/specs/ in 2/2 runs; both
  path mentions now explicitly forbid the shortening.

TDD evidence (quorum):
- RED: batch-20260609T023452Z-68aa et al — 5/5 agents fail
- GREEN: cost-spec-plan-duplication-claude-20260609T234142Z-9625 pass
  (plan: "this plan does not restate them" + spec cited by path;
  both docs in docs/superpowers/)
- Canary: triggering-writing-plans-claude pass (skill still fires)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-09 16:52:21 -07:00
7 changed files with 9 additions and 38 deletions

2
evals

Submodule evals updated: f8e5a9949f...ff3ee83f94

View File

@@ -109,7 +109,8 @@ digraph brainstorming {
**Documentation:** **Documentation:**
- Write the validated design (spec) to `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md` - Write the validated design (spec) to `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md`
- (An explicit user instruction overrides this default; an existing differently-named docs directory does not) - The `docs/superpowers/` prefix is the convention; do not shorten it to `docs/specs/`
- (User preferences for spec location override this default)
- Use elements-of-style:writing-clearly-and-concisely skill if available - Use elements-of-style:writing-clearly-and-concisely skill if available
- Commit the design document to git - Commit the design document to git

View File

@@ -16,7 +16,7 @@ Load plan, review critically, execute all tasks, report when complete.
## The Process ## The Process
### Step 1: Load and Review Plan ### Step 1: Load and Review Plan
1. Read plan file, and the spec it cites in its `**Spec:**` header (plans reference requirements rather than restating them) 1. Read plan file
2. Review critically - identify any questions or concerns about the plan 2. Review critically - identify any questions or concerns about the plan
3. If concerns: Raise them with your human partner before starting 3. If concerns: Raise them with your human partner before starting
4. If no concerns: Create todos for the plan items and proceed 4. If no concerns: Create todos for the plan items and proceed

View File

@@ -86,10 +86,6 @@ digraph process {
} }
``` ```
## Spec Context
If the plan's header cites a spec (`**Spec:** <path>`), read it once during plan extraction. Plans reference requirements rather than restating them — when a task cites a spec section, paste that section's text into the implementer and spec-reviewer prompts along with the task text. Implementer subagents never read the spec file themselves; the spec reviewer may additionally read it at the cited path (its prompt says so).
## Model Selection ## Model Selection
Use the least powerful model that can handle each role to conserve cost and increase speed. Use the least powerful model that can handle each role to conserve cost and increase speed.

View File

@@ -12,8 +12,6 @@ Subagent (general-purpose):
[FULL TEXT of task from plan - paste it here, don't make subagent read file] [FULL TEXT of task from plan - paste it here, don't make subagent read file]
[If the task cites spec sections, paste the cited sections' text here too]
## Context ## Context
[Scene-setting: where this fits, dependencies, architectural context] [Scene-setting: where this fits, dependencies, architectural context]

View File

@@ -12,7 +12,7 @@ Subagent (general-purpose):
## What Was Requested ## What Was Requested
[FULL TEXT of task requirements, including the text of any spec sections the task cites] [FULL TEXT of task requirements]
## What Implementer Claims They Built ## What Implementer Claims They Built
@@ -28,7 +28,7 @@ Subagent (general-purpose):
git diff [BASE_SHA]..[HEAD_SHA] git diff [BASE_SHA]..[HEAD_SHA]
``` ```
Only read files in this diff. Do not crawl the broader codebase. (One exception: if the requirements cite a spec document, you may read that spec at its cited path.) Only read files in this diff. Do not crawl the broader codebase.
## Read-Only Review ## Read-Only Review

View File

@@ -11,16 +11,14 @@ Write comprehensive implementation plans assuming the engineer has zero context
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well. Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
**Plans reference the spec; they never restate, paraphrase, or summarize it.** The spec owns the WHAT and WHY — requirements, acceptance criteria, design decisions; the plan owns the HOW — tasks, files, code, commands. Cite it by path in the header and by section where a task needs context. Reference discipline never means skipping the spec: if brainstorming produced one, it exists and the plan cites it. No Placeholders still requires repeating code and commands WITHIN the plan; copying FROM the spec is different: a step that needs a requirement's prose is under-specified — turn it into a concrete action. Snapshotting spec text into the plan hides drift, not prevents it. "Zero context" means each step is mechanically executable, not that the plan repeats the spec. **Plans reference the spec; they never restate it.** The spec owns the WHAT and WHY — requirements, acceptance criteria, design decisions. The plan owns the HOW — tasks, files, code, commands. Cite the spec by path in the header and by section where a task needs context. Re-deriving spec content inline doubles the documents and lets them drift apart. "Zero context" means the engineer can execute each step mechanically; it does not mean the plan repeats what the spec already says — they can read the spec at the cited path.
**Two narrow exceptions to reference discipline** — subagents executing the plan see the plan (or a single task of it), never the spec, so two kinds of spec content travel in the plan itself: the `## Global Constraints` section (the spec's project-wide requirements, exact values copied verbatim) and each task's `**Interfaces:**` block (exact signatures). Copy those values exactly; everything else stays referenced, never restated.
**Announce at start:** "I'm using the writing-plans skill to create the implementation plan." **Announce at start:** "I'm using the writing-plans skill to create the implementation plan."
**Context:** If working in an isolated worktree, it should have been created via the `superpowers:using-git-worktrees` skill at execution time. **Context:** If working in an isolated worktree, it should have been created via the `superpowers:using-git-worktrees` skill at execution time.
**Save plans to:** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md` **Save plans to:** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`
- (An explicit user instruction overrides this default; an existing differently-named docs directory does not) - (User preferences for plan location override this default)
## Scope Check ## Scope Check
@@ -37,15 +35,6 @@ Before defining tasks, map out which files will be created or modified and what
This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently. This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.
## Task Right-Sizing
A task is the smallest unit that carries its own test cycle and is worth a
fresh reviewer's gate. When drawing task boundaries: fold setup,
configuration, scaffolding, and documentation steps into the task whose
deliverable needs them; split only where a reviewer could meaningfully
reject one task while approving its neighbor. Each task ends with an
independently testable deliverable.
## Bite-Sized Task Granularity ## Bite-Sized Task Granularity
**Each step is one action (2-5 minutes):** **Each step is one action (2-5 minutes):**
@@ -66,19 +55,12 @@ independently testable deliverable.
**Goal:** [One sentence describing what this builds] **Goal:** [One sentence describing what this builds]
**Spec:** [Path to the spec doc, e.g. `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md` — requirements and design decisions live there; do not restate them here. Only if no spec doc exists (requirements arrived conversationally; brainstorming never ran): write "none — requirements:" and state them once here, not per task] **Spec:** [Path to the spec doc, e.g. `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md` — requirements and design decisions live there; do not restate them here]
**Architecture:** [2-3 sentences about approach] **Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries] **Tech Stack:** [Key technologies/libraries]
## Global Constraints
[The spec's project-wide requirements — version floors, dependency limits,
naming and copy rules, platform requirements — one line each, with exact
values copied verbatim from the spec. Every task's requirements implicitly
include this section.]
--- ---
``` ```
@@ -92,12 +74,6 @@ include this section.]
- Modify: `exact/path/to/existing.py:123-145` - Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py` - Test: `tests/exact/path/to/test.py`
**Interfaces:**
- Consumes: [what this task uses from earlier tasks — exact signatures]
- Produces: [what later tasks rely on — exact function names, parameter
and return types. A task's implementer sees only their own task; this
block is how they learn the names and types neighboring tasks use.]
- [ ] **Step 1: Write the failing test** - [ ] **Step 1: Write the failing test**
```python ```python