Skip to content

existential-birds/beagle / plugins/beagle-analysis/skills/write-plan

write-plan

Verified

Use when you have a finalized brainstorm-beagle spec at `.beagle/concepts/<slug>/spec.md` and need a bite-sized, TDD-driven implementation plan before any code is written. Triggers on: "write a plan", "plan this spec", "turn the spec into a plan", "now plan the implementation", "write-plan". Reads the spec, designs the file structure, decomposes work into 2-5 minute TDD steps with exact paths and commands, self-reviews against the spec, gets user approval, then writes to `.beagle/concepts/<slug>/plan.md` and offers to generate an execution handoff prompt via the subagent-prompt skill. Does NOT brainstorm specs, write code, or execute the plan — produces the plan document (and an optional handoff prompt) only.

FileKindSize
SKILL.mdskill md41.4 KB
references/plan-reviewer.mdmarkdown4.4 KB
references/plan-template.mdmarkdown12.3 KB

references/plan-reviewer.md

View on GitHub
# Plan Document Reviewer Prompt Template

Use this template when dispatching a plan-document reviewer subagent.

**Purpose:** Verify the plan is complete, matches the spec, and has proper task decomposition.

**Dispatch when:** The plan is long (>10 tasks), touches unfamiliar territory, or has high stakes. For short, familiar plans, skip the dispatched review — the self-review and the human review step are enough.

**Dispatch after:** The complete plan draft is written and self-review has been honestly passed. Do not dispatch the reviewer to do your self-review for you.

## Prompt Template

```text
Reviewer brief (dispatch as a subagent if supported, otherwise run inline):

    You are a plan document reviewer. Verify this implementation plan is complete and ready for execution.

    **Plan to review:** [PLAN_FILE_PATH or inline draft]
    **Source spec:** [SPEC_FILE_PATH at .beagle/concepts/<slug>/spec.md]
    **Project conventions:** [path(s) to relevant AGENTS.md or CLAUDE.md]

    ## What to Check

    | Category | What to Look For |
    |----------|------------------|
    | Spec coverage | Every must-have requirement from the spec has a task that implements it. List any gaps. |
    | Test discipline | Every behavior-changing task has a failing-test step before the implementation step. Flag tasks that implement without a test. |
    | Consumer check | Every new public API surface (trait method, exported fn, public field, endpoint, CLI flag) has a named production consumer — a caller on a non-test path — in this same plan. A contract/unit test is NOT a consumer. Flag any surface whose only caller is a test; it must be cut or tagged deferred with a numbered follow-up. |
    | Discriminating assertion | For each test, a plausible broken/no-op impl that still passes the assertion means the assertion is on the wrong target. For preserve/recover/transform invariants: the sentinel must be asserted in the region the bug damages (the dropped middle, never the surviving head/tail), through every structurally-distinct producer (streaming-with-eviction vs whole-string). Flag any test a no-op impl would still pass. |
    | Assertion quality | Tests assert observable consequences (DB rows, files written, user-visible output), not dispatch ("the handler was called"). Flag dispatch-only assertions. |
    | Placeholders | TBD, TODO, "implement later", "similar to Task N", `unimplemented!()`, vague verbs without code. |
    | Type consistency | Function names, type names, and signatures match across tasks. `clearLayers()` in Task 3 vs `clearFullLayers()` in Task 7 is a bug. |
    | Project conventions | The plan respects CLAUDE.md rules — test tiers, comment policy, commit format, forbidden patterns. |
    | Out-of-scope creep | No task implements something the spec explicitly marks Out of Scope. |
    | Assumptions | Load-bearing assumptions are surfaced in the Assumptions section, not baked silently into tasks. |

    ## Calibration

    **Only flag issues that would cause real problems during execution.**

    An executor (engineer or agent) building the wrong thing, getting stuck on a placeholder, or shipping broken-but-green tests is a real problem. Minor wording, stylistic nits, and "could be more detailed" suggestions are not.

    Approve unless there are serious gaps:
    - Missing requirements from the spec
    - Contradictory or out-of-order steps
    - Placeholder content where real code/commands are required
    - Tests that assert dispatch instead of consequence
    - A new public surface with no production consumer
    - A test whose assertion a no-op impl would still pass / a payload-preservation test that checks only the surviving head-tail
    - Tasks so vague they can't be acted on

    ## Output Format

    ## Plan Review

    **Status:** Approved | Issues Found

    **Issues (if any):**
    - [Task X, Step Y]: [specific issue] — [why it matters for execution]

    **Recommendations (advisory, do not block approval):**
    - [suggestions for improvement]
```

## What to Do With the Reviewer Output

- **Status: Approved** — proceed to user review. Mention to the user that the dispatched review passed.
- **Status: Issues Found** — fix each blocking issue inline, then either re-dispatch (if a second pass is justified) or proceed to user review with a note about what was fixed.

Do NOT treat the reviewer's recommendations as mandatory. They're advisory. Apply the ones that obviously improve the plan; skip the ones that are stylistic preference.
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall