planner-manager-explorer
Use when a planning or manager agent must maintain architecture, framework decomposition, TODO tables, and next-session objectives while also exploring…
Skill by waltstephen
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/waltstephen-planner-manager-explorer
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: productivity, agent-building
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 and code. 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/planner-manager-explorer
What's inside
- Skill name
planner-manager-explorer- Description
- Use when a planning or manager agent must maintain architecture, framework decomposition, TODO tables, and next-session objectives while also exploring missing context from the repository, official docs, external APIs, datasets, or similar open-source projects before handing concrete work to an execution agent.
- License
- MIT
- Instructions
- 69 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Planner Manager Explorer Operate as a manager-plus-explorer, not a passive status summarizer. ## Core Role For each planning pass: 1. Maintain the current framework: what exists, what is missing, what is risky. 2. Keep workstreams concrete and execution-oriented. 3. Discover adjacent high-value expansions when they are grounded in the repo and user goal. 4. Turn open questions into explicit exploration items. 5. Produce one follow-up objective that a separate execution session can run directly. ## Working Style Use this loop: 1. Inspect repo state, git diff, recent summaries, and operator messages. 2. Update the architecture map and workstream table. 3. Identify missing data, missing integrations, missing validation, or missing product surface. 4. If external knowledge is required, browse primary or official sources first. 5. If useful, compare with one or two similar open-source projects to avoid reinventing obvious patterns. 6. Convert findings into: - workstreams - remaining items - exploration backlog - next executable objective ## Explorer Rules When gaps depend on external context, do not stop at "needs research". Research actively for: 1. Official API docs 2. SDK docs 3. Public datasets 4. Similar open-source implementations 5. Integration constraints that affect architecture Prefer: 1. Official docs over blog posts 2. Primary sources over summaries 3. Short evidence-backed notes over long prose ## Architecture Bias Push planning toward: 1. Clear module boundaries 2. Explicit interfaces and data flow 3. Validation strategy 4. Operational hooks for future extension 5. Backlog items that are specific enough for an intern-style executor ## Output Contract Always leave behind: 1. A workstream table with status, evidence, and next step 2. A TODO board that can be maintained across sessions 3. An explorer backlog for unresolved research 4. One concrete next-session objective when follow-up execution is justified If the user modifies the plan, inherit the existing plan instead of starting from zero unless the user explicitly resets scope.
From waltstephen/ArgusBot, MIT.
More from waltstephen/ArgusBot
- 0.620score
autonomous-research-loop
waltstephen
Operate Codex as a high-autonomy repository executor for implementation, debugging, and long-running research loops.
SkillDFreshness: D★ 315Claude Code +9 - 0.620score
pptx-run-report
waltstephen
Use this skill any time a .pptx file is involved — creating, reading, editing, or generating a run report presentation.
SkillDFreshness: D★ 315Claude Code +9 - 0.620score
final-task-report
waltstephen
Use when the main execution agent must produce a final Markdown delivery report after the task is complete, especially when reviewer status is done and the…
SkillDFreshness: D★ 315Claude Code +9 - 0.536score
btw-file-return
waltstephen
Detect when a BTW question is asking for project files, screenshots, or effect images, then return the most relevant local file paths quickly.
SkillDFreshness: D★ 315Claude Code +9
Signals
- Stars
- 315
- Forks
- 29
- Open issues
- 0
- Last commit (this folder)
- Mar 11, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/waltstephen/ArgusBot
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from waltstephen
- 0.620score
autonomous-research-loop
waltstephen
Operate Codex as a high-autonomy repository executor for implementation, debugging, and long-running research loops.
SkillDFreshness: D★ 315Claude Code +9 - 0.620score
pptx-run-report
waltstephen
Use this skill any time a .pptx file is involved — creating, reading, editing, or generating a run report presentation.
SkillDFreshness: D★ 315Claude Code +9 - 0.620score
final-task-report
waltstephen
Use when the main execution agent must produce a final Markdown delivery report after the task is complete, especially when reviewer status is done and the…
SkillDFreshness: D★ 315Claude Code +9 - 0.536score
btw-file-return
waltstephen
Detect when a BTW question is asking for project files, screenshots, or effect images, then return the most relevant local file paths quickly.
SkillDFreshness: D★ 315Claude Code +9
Cite this page
planner-manager-explorer skill. Agent Mart. https://agentmart.dev/skills/waltstephen-planner-manager-explorer (last updated 2026-10-24)