Review Plan

Review Plan

Review a planning artifact against type-specific criteria. Runs internal reviews and /peer-review in parallel by default. Returns combined structured findings.

Step 1: Determine Artifact Type and Resolve

Determine Artifact Type

• Explicit argument — If the user specified a type (e.g., "review shells", "review spec"), use it. No argument defaults to plan.
• Conversation context — If artifact text or a path is already in context, infer the type.
• Auto-detect — Check .turbo/ for existing artifacts. If multiple types exist, pick the one with the most recently modified file.

Resolve the Artifact

Plan (default)

• Plan text in conversation — use it
• Explicit path — read it
• Explicit slug — resolve to .turbo/plans/<slug>.md
• Single file — Glob .turbo/plans/*.md. If exactly one file exists, use it
• Most recent — most recently modified file
• Legacy fallback — .turbo/plan.md if .turbo/plans/ does not exist
• Nothing found — stop and state that no artifact was found to review

Shells

• Shell text in conversation — use it
• Explicit spec slug — Glob .turbo/shells/<slug>-*.md
• Explicit spec path — derive slug from filename, glob as above
• Single spec — Glob .turbo/specs/*.md. If exactly one, derive slug and glob for shells
• Most recent spec — most recently modified spec, derive slug and glob
• Nothing found — stop and state that no artifact was found to review

For shells, read each shell file and parse its YAML frontmatter (spec, depends_on). Read the source spec from the spec field.

Spec

• Spec text in conversation — use it
• Explicit path — read it
• Explicit slug — resolve to .turbo/specs/<slug>.md
• Single file — Glob .turbo/specs/*.md. If exactly one, use it
• Most recent — most recently modified
• Legacy fallback — .turbo/spec.md if .turbo/specs/ does not exist
• Nothing found — stop and state that no artifact was found to review

If multiple candidates exist, pick the most recently modified.

Step 2: Run Reviews in Parallel

Each artifact type has two reference files, one per internal review:

• Plan — references/plan-structure-review.md, references/plan-scope-review.md
• Shells — references/shells-structure-review.md, references/shells-scope-review.md
• Spec — references/spec-structure-review.md, references/spec-scope-review.md

Skip peer review when instructed (e.g., "without peer review", "no peer", "internal only").

Use the Agent tool to launch all agents below in a single assistant message so they run concurrently. Run them in the foreground so all their results return in this turn. Each Agent call uses model: "opus" and no name. That is three Agent tool calls when peer review is active (two internal + one peer), or two Agent tool calls when peer review is skipped. Every agent's prompt must direct it to treat the shared working tree and its git index as read-only and to assess findings by reading and reasoning. For a check that genuinely requires mutating code (such as testing whether a finding holds), the agent works in an isolated git worktree created under $TMPDIR and discarded afterward. Give that worktree its own dependency install rather than reaching the shared tree's install by any route: removing a worktree deletes through symlinks, and a redirected suite writes into the shared install. When its own install is not possible, the check is left unrun and reported as such. Afterward the agent verifies that git worktree list no longer shows the worktree, that git status --short is clean, and that the shared tree's dependency directory still resolves (a destroyed install leaves git status clean, since it is gitignored). Damage the agent cannot repair is reported with the exact repair command in place of findings.

• Structure Agent: The subagent's prompt must include the artifact text, the path to the type's structure reference file (~/.claude/skills/review-plan/references/<type>-structure-review.md), the output format below, and this directive: read that reference file directly, apply its determination criteria as the bar for a real finding, then report every finding that clears that bar tagged with its priority and with internal (structure). Coverage is the goal at this stage, so surface everything that qualifies and let the priority tags convey severity. The subagent must also return the Overall Verdict block for its dimension.
• Scope Agent: Same, with the type's scope reference file (~/.claude/skills/review-plan/references/<type>-scope-review.md) and findings tagged internal (scope).
• Peer review Agent (unless skipping): Launch an Agent tool call whose prompt instructs the subagent to invoke /peer-review via the Skill tool with a request describing: (a) the artifact under review; (b) the criteria live in ~/.claude/skills/review-plan/references/<type>-structure-review.md and ~/.claude/skills/review-plan/references/<type>-scope-review.md for the resolved type from Step 1 — the reviewer should read both files directly and cover every criterion in one single-pass review, applying each file's determination criteria and priority scale to the findings in that file's domain; (c) the Overall Verdict should use the Readiness: <ready | needs revision> label. The prompt must also state explicitly that the subagent's final assistant message must contain the verbatim findings text /peer-review produced.

Aggregate findings with attribution (reviewer: "internal" or "peer", each with its "structure" or "scope" dimension). Present them in the output format below.

Then use the TaskList tool and proceed to any remaining task.

Output Format

Format each finding as:

### [P<N>] <title (imperative, ≤80 chars)>

**Section:** <plan section, shell number(s), or spec section>
**Reviewer:** <internal | peer> (<structure | scope>)

<one paragraph explaining the issue and its impact>

After all findings, place the Overall Verdict block each internal subagent returned for its dimension, then a single combined block for the peer review:

## Overall Verdict: <Structure | Scope>

**Readiness:** <ready | needs revision>

<1-3 sentence assessment>

## Peer Review Verdict

**Readiness:** <ready | needs revision>

<1-3 sentence assessment>

If there are no qualifying findings, state so and explain briefly.

Rules

• Present findings grouped by priority.