agentsclimarketplace
Sign in

Plan mode

Skill CodeAlive-AI/ai-driven-development/skills/plan-mode

Use this skill when the user asks to plan, design, scope, estimate, or implement a feature, bug fix, refactor, migration, integration, API change, UI change, or other project modification. Enforces a planning gate before editing code — investigate project context, analyze the task, surface ambiguities, contradictions, risks, dependencies, and blockers, ask focused questions, produce an evidence-based step-by-step plan, and implement only after explicit user approval. Not for trivial one-line edits, pure questions about the codebase, or changes the user has already reviewed and approved for direct implementation.From its SKILL.md

Install
npx -y skills add CodeAlive-AI/ai-driven-development --skill plan-mode

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

3.3 KB, 573 tokens by cl100k_base, as published. Nobody here has run it

Plan Mode

Prevent premature implementation. Understand → plan → get approval → implement → validate. Do not skip the gate just because a change looks small.

The full protocol — investigation steps, issue classification, the question and plan templates, validation, and special cases — lives in PROTOCOL.md. Read it before planning or implementing.

Default behavior

  1. Investigate project context (read-only).
  2. Analyze the task: goal, current vs desired behavior, acceptance criteria, scope, edge cases.
  3. Classify open issues as ambiguity / contradiction / blocker / risk / assumption.
  4. Ask the smallest set of focused questions that unblocks planning.
  5. Produce a consistent, evidence-based, step-by-step plan.
  6. Wait for explicit approval.
  7. Implement only the approved plan.
  8. Validate, then report what was and was not checked.

The gate (core rule)

During Plan Mode, do not mutate the project: no editing files, scaffolding, patches, package installs, lockfile updates, migrations, deploys, destructive scripts, or "trying an implementation" to learn the code.

Allowed: read files, search the repo, inspect structure, review tests / docs / configs / API contracts / schemas / migrations, run read-only or non-mutating diagnostic commands, and consult external docs when project context is insufficient.

If a tool or command might mutate state, ask first or avoid it.

Surfacing blockers

Surface ambiguities, contradictions, and blockers before the plan — never bury them inside it. For each, capture: what it is, the evidence, why it matters, whether it blocks implementation, and a proposed default or resolution. If none exist, state No hard blockers found.

Asking questions

Ask only after investigating context, and never for what the repo, tests, docs, or provided context already answer. Group related questions, give each a recommended default, and explain briefly why each answer matters. Avoid open-ended "What should I do?" questions.

Approval

Counts as approval: an explicit "proceed / implement / apply / go ahead / approve", or an edited plan with a clear instruction to continue. Does not count: answering one question, commenting on the plan, asking for more detail or alternatives, or "is this enough?". When approval is ambiguous, ask for a direct confirmation.

If new evidence contradicts the approved plan mid-implementation, pause and return to planning with what changed, the evidence, the impact, and a revised recommendation.

Reference

Full protocol, output templates, and special handling (small tasks, urgent fixes, user-provided plans, partial context): PROTOCOL.md.

What ships with it: 2 files

16.3 KB alongside SKILL.md

Gives 1 of the 12 instructions most plan spec skills give in 573 tokens

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 approvalhere, and in 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

  • Investigate project context first
  • Classify open issues
  • Ask focused questions
  • Produce a step-by-step plan
  • Implement only the approved plan
  • Validate the implementation

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.