Planning implementation
Tactical planning methodology for the planner agent — the plan.md document template that expands each vertical slice into file-level steps, and the tactical rules that keep the plan scannable and scoped. Loaded when a structure is translated into the implementer's playbook.From its SKILL.md
npx -y skills add bostonaholic/team --skill planning-implementationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 11 stars11 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.9 KB, as published. Nobody here has run it
Planning Implementation
The planner's methodology: expand each vertical slice from the structure into precise file-level steps with acceptance-test mappings.
Plan structure
The body of plan.md:
# Plan: <topic>
## Context
Two to three sentences summarizing the change. Reference the
structure by path. In multi-repo mode, list the repo slugs and their
worktree paths (read from repos.md `## Worktrees` once the worktrees
exist) so the implementer knows where to cd for each step.
## Slices
For each slice from structure.md, expand it into file-level steps.
### Slice 1: <name from structure.md>
**Repos:** <multi-repo only — comma-separated repo slugs>
**Acceptance tests** (from structure.md):
- `test_name_1` — what it asserts
(multi-repo: `<repo>:test_name_1`)
- `test_name_2` — what it asserts
**Steps:**
1. `path/to/file.ts` — <what to add/modify/remove. Reference patterns to
follow with file:line. Mark as `[parallel]` or `[sequential]`.>
(multi-repo: prefix the file path with the repo slug, e.g.
`[repo: api] path/to/file.ts` — the implementer cd's into that repo's
worktree before applying the step)
2. `path/to/other.ts` — ...
**Verification:** Run `<command>`. The slice is done when its acceptance
tests pass and prior slices' tests still pass.
(multi-repo: list one verification command per repo, scoped to that
repo's worktree)
**Commit:** `<conventional-commit subject for this slice>`
(multi-repo: when the slice spans repos, list one **Commit** per repo;
the implementer creates one commit per repo, all with the same slice
context referenced in the body)
### Slice 2: <name>
...
## Done Criteria
- All acceptance tests for every slice pass
- No regressions in existing tests
- Any additional criteria specific to this feature
- (multi-repo) every involved repo's worktree has only the commits this
topic produced — no incidental edits in other repos
Tactical rules
- One slice at a time. Steps within a slice may parallelize, but slices themselves are sequential. The implementer commits each slice atomically.
- Reuse, do not reinvent. Reference existing functions, utilities, and patterns from research.md.
- Stay under 300 lines. The plan must be scannable in one sitting.
- No implementation code. Describe what to build and where. Leave how (the actual code) to the implementer.
- Atomic slices. Each slice should leave the codebase in a working state with its acceptance tests passing.
- Test coverage matches the structure. Do not add tests beyond what the structure specifies — the structure is the scope fence.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most plan spec skills give
Counted across 1,360 of the 2,617 authors here whose files we hold, read 2026-09-06
- Ask one question at a timein 73 of 1360
- Write the spec using the templatein 22 of 1360
- Ask clarifying questions if neededin 19 of 1360, across 18 files
- Wait for user confirmation before proceedingin 19 of 1360
- Save plans to the plans directoryin 17 of 1360, across 13 files
- Check for product marketing context firstin 16 of 1360, across 5 files
- Read the plan file completelyin 16 of 1360
- Order tasks by dependencyin 16 of 1360
- Gather context from the conversationin 15 of 1360, across 9 files
- Explore the codebase instead of askingin 15 of 1360, across 13 files
- Wait for explicit user approvalin 14 of 1360, across 13 files
- Quiz the user on the breakdownin 13 of 1360, across 7 files
Said here and by no other author read
- Expand each vertical slice into file-level steps
- Keep the plan under 300 lines
- Make each slice atomic
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.