Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/bibutikoley-plan
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/plan
What's inside
- Skill name
plan- Description
- Stage 3 (Build) entry of the AI-native SDLC. In plan mode, interview the engineer against an accepted spec.md and produce a committed plan.md (files that change, order of work, risks, options not taken, proof) before any code is written. Use on /sdlc:plan or when asked to plan a change that has a spec.
- License
- MIT
- Instructions
- 47 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /sdlc:plan — plan before code Read `sdlc-loop`. Design review happens here, while changing course is still a matter of editing a document. ## Preconditions 1. Resolve the change from `$ARGUMENTS` (or list changes with an accepted `spec.md` and no `plan.md`). 2. `spec.md` must be `status: accepted`. If not, name the product owner and stop, unless `--no-spec` or an explicit override is given (record `override:` in the plan frontmatter). Small changes without an intent may run with `--no-spec`; still write a plan. 3. **Enter plan mode now** (call `EnterPlanMode`). You may read the codebase freely and must not edit files until the engineer accepts the plan. Write `.sdlc/current` with the change id (allowed: it is a marker, not code) once the plan is accepted, not before. ## Interview, then draft Read `intent.md`, `spec.md`, `CLAUDE.md`, and the code the spec names. Then interview the engineer briefly: - Which files change, and is there existing code to reuse rather than add? - What order minimises risk (behind auth first, UI last, migrations separately)? - Which tests prove each acceptance criterion? What is the quantifiable "done"? Draft `plan.md` from `sdlc/changes/_template/plan.md`, setting `spec_commit` to the accepted spec SHA. ## Interrogate the plan (mandatory, before asking for approval) Answer these in the plan itself: 1. What could this change break? (Risks) 2. Which step is the riskiest, and how is it made safe? 3. What other options did you choose not to do, and why? (Options not taken) 4. Could an engineer who never saw this conversation implement it from the plan alone? Iterate until yes. 5. Can the work be split into independent tasks that touch different files? Mark them; the engineer may run them as parallel sessions in worktrees (`claude --worktree <task>`). Tasks sharing files stay in one session. ## Accept and commit - Present the plan for approval (ExitPlanMode). Routine changes are accepted by the engineer. If `risk: high`, say a tech lead or architect must also approve before build, and stop after committing the draft. - On acceptance: set `status: accepted`, write `.sdlc/current` = change id, commit `plan: <title>` with trailer `SDLC-Change: <id>` on the working branch `sdlc/<change-id>`. - Report: path, the proof statement, the parallelisable tasks, and the next step: `/sdlc:build`. ## Rules - Never write application code in this skill. Plan mode enforces it; respect it. - The plan is the contract review checks against (Stage 5). Be exact about paths and tests. - With a solid plan, implementation is usually a single pass. Spend the time here.
From bibutikoley/ai-sdlc-claude, MIT.
More from bibutikoley/ai-sdlc-claude
- 0.564score
tracker-sync
bibutikoley
Keep the legacy tracker (Jira, YouTrack, GitLab issues, GitHub issues) and the Markdown artifacts linked according to sdlc.config.json sourceOfTruth (repo |…
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
security-policy
bibutikoley
The organisation's security policy as constraints on specs, plans, code and reviews.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
ux-standards
bibutikoley
Interaction, accessibility and content-structure standards for anything users touch.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
release
bibutikoley
Stage 5 (Deploy) release of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
review
bibutikoley
Stage 5 (Deploy) AI review of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
setup
bibutikoley
Install the AI-native SDLC loop into a product repository.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
spec
bibutikoley
Stage 2 (Design) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
eval-add
bibutikoley
Stage 4 (Test) continuous evals.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
incident
bibutikoley
Stage 6 (Maintain) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
intent
bibutikoley
Stage 1 (Plan) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
metrics
bibutikoley
Compute and explain the AI-native SDLC's leading and lagging indicators from Git history, PR metadata and CI (intent time-to-commit, intent→spec, spec→plan…
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
brand-guidelines
bibutikoley
The organisation's brand and content standards applied to specs and UI work.
SkillBFreshness: B★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 5, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bibutikoley/ai-sdlc-claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bibutikoley
- 0.564score
brand-guidelines
bibutikoley
The organisation's brand and content standards applied to specs and UI work.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
eval-add
bibutikoley
Stage 4 (Test) continuous evals.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
incident
bibutikoley
Stage 6 (Maintain) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
intent
bibutikoley
Stage 1 (Plan) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
metrics
bibutikoley
Compute and explain the AI-native SDLC's leading and lagging indicators from Git history, PR metadata and CI (intent time-to-commit, intent→spec, spec→plan…
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
compliance-policy
bibutikoley
Regulatory and change-management obligations as constraints on specs, plans, releases and reviews.
SkillBFreshness: B★ 3Claude Code +9
Cite this page
plan skill. Agent Mart. https://agentmart.dev/skills/bibutikoley-plan (last updated 2026-10-24)