prometheus-plan
Strategic planning mode (/plan): interview, gap analysis, write work plans under .omg/plans/, optional review, then /start-work to activate boulder execution.
Skill by mihazs
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/mihazs-prometheus-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
Use cases: writing
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/prometheus-plan
What's inside
- Skill name
prometheus-plan- Description
- Strategic planning mode (/plan): interview, gap analysis, write work plans under .omg/plans/, optional review, then /start-work to activate boulder execution.
- License
- MIT
- Instructions
- 57 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Prometheus Plan (`/plan`) ## Purpose Use `/plan` (or `/prometheus`) when you need a **work plan before implementation**. Planning mode blocks non-markdown writes outside `.omg/` until `/start-work`. --- ## 5-Step Workflow ### Step 1 — Interview - Classify intent (trivial, refactor, greenfield, architecture, etc.). - Ask focused questions; record decisions in `.omg/drafts/<topic>.md`. - Do **not** implement product code in plan mode. ### Step 2 — Research (parallel) - `Task(subagent_type="explore", ...)` for codebase patterns, references, tests. - `Task(subagent_type="librarian", ...)` for external docs when needed. - Do not duplicate the same search after delegating. ### Step 3 — Metis gap analysis - `Task(subagent_type="metis-consultant", prompt="Review draft + requirements; list gaps and blocking questions.")` - Resolve gaps with the user before writing the final plan. ### Step 4 — Write the plan - Single plan file: `.omg/plans/<name>.md` - Use skeleton Write + Edit batches for large TODO lists (see prometheus-planner agent). - Include waves, dependencies, QA scenarios, and Final Verification Wave. ### Step 5 — Momus review (optional) → start work - `Task(subagent_type="momus-reviewer", prompt="Review .omg/plans/<name>.md; verdict OKAY or NEEDS_REVISION.")` - Fix revisions until OKAY or user accepts risk. - User runs `/start-work .omg/plans/<name>.md` to write `.omg/boulder.json` and exit plan mode. --- ## Commands | Command | Effect | |---------|--------| | `/plan` | Enable plan mode + planning instructions | | `/cancel-plan` | Disable plan mode | | `/start-work <plan.md>` | Write `boulder.json` (schema v2), disable plan mode | --- ## Constraints (enforced by hooks) - **Allowed writes in plan mode:** `.omg/**/*.md` only - **Forbidden:** source edits, deletes outside that pattern - **Execution:** only after `/start-work`
From mihazs/oh-my-grok, MIT.
More from mihazs/oh-my-grok
- 0.542score
agent-skill-gate
mihazs
MANDATORY before code changes, debugging, planning, or multi-step implementation in ANY repository.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
handoff
mihazs
Create a detailed HANDOFF CONTEXT summary for continuing work in a new Grok session.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
ralph-loop
mihazs
Start a Ralph Loop — autonomous work-until-done via Stop-hook continuations.
SkillCFreshness: C★ 11Claude Code +9 - 0.539score
ulw-loop
mihazs
Start an ULTRAWORK loop — Ralph loop plus mandatory Oracle verification before exit.
SkillCFreshness: C★ 11Claude Code +9 - 0.539score
hashline-edit
mihazs
Hash-anchored StrReplace edits using LINE#ID tags from Read output.
SkillCFreshness: C★ 11Claude Code +9 - 0.539score
lsp
mihazs
Language Server Protocol tools via the bundled lsp MCP server — diagnostics, navigation, symbols, and rename.
SkillCFreshness: C★ 11Claude Code +9 - 0.539score
ast-grep
mihazs
Structural code search and rewrite via the bundled ast_grep MCP server.
SkillCFreshness: C★ 11Claude Code +9 - 0.537score
cancel-ralph
mihazs
Cancel an active Ralph or Ultrawork loop.
SkillCFreshness: C★ 11Claude Code +9 - 0.517score
finishing-a-development-branch
mihazs
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting…
SkillCFreshness: C★ 11Claude Code +9 - 0.516score
requesting-code-review
mihazs
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
SkillCFreshness: C★ 11Claude Code +9 - 0.516score
writing-plans
mihazs
Use when you have a spec or requirements for a multi-step task, before touching code
SkillCFreshness: C★ 11Claude Code +9 - 0.516score
subagent-driven-development
mihazs
Use when executing implementation plans with independent tasks in the current session
SkillCFreshness: C★ 11Claude Code +9
Signals
- Stars
- 11
- Forks
- 5
- Open issues
- 0
- Last commit (this folder)
- Jun 3, 2026 (4 months ago)
- Last release
- Jun 3, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mihazs/oh-my-grok
- Website
- github.com/mihazs/oh-my-grok
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mihazs
- 0.542score
agent-skill-gate
mihazs
MANDATORY before code changes, debugging, planning, or multi-step implementation in ANY repository.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
handoff
mihazs
Create a detailed HANDOFF CONTEXT summary for continuing work in a new Grok session.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
ralph-loop
mihazs
Start a Ralph Loop — autonomous work-until-done via Stop-hook continuations.
SkillCFreshness: C★ 11Claude Code +9 - 0.539score
ast-grep
mihazs
Structural code search and rewrite via the bundled ast_grep MCP server.
SkillCFreshness: C★ 11Claude Code +9 - 0.539score
hashline-edit
mihazs
Hash-anchored StrReplace edits using LINE#ID tags from Read output.
SkillCFreshness: C★ 11Claude Code +9 - 0.539score
lsp
mihazs
Language Server Protocol tools via the bundled lsp MCP server — diagnostics, navigation, symbols, and rename.
SkillCFreshness: C★ 11Claude Code +9
Cite this page
prometheus-plan skill. Agent Mart. https://agentmart.dev/skills/mihazs-prometheus-plan (last updated 2026-10-24)