plan-task
Use Snipara's planning tools when the user asks you to implement a complex feature, refactor code, or tackle a multi-step task.
Skill by Snipara
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/snipara-plan-task
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
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-task
What's inside
- Skill name
plan-task- Description
- Use Snipara's planning tools when the user asks you to implement a complex feature, refactor code, or tackle a multi-step task. Generate execution plans before starting work.
- License
- MIT
- Instructions
- 25 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
When the user asks you to implement something complex:
1. First check if it's complex enough:
- Affects 5+ files? → Use planning
- Multiple sub-tasks? → Use planning
- Architectural decisions? → Use planning
2. Use `mcp__snipara__rlm_plan` with:
- `query`: The task description
- `max_tokens`: 16000 for comprehensive plans
- `strategy`: "relevance_first" (default) or "depth_first"
3. Or use `mcp__snipara__rlm_decompose` to break into chunks:
- `query`: The task
- `max_depth`: 2 (recommended)
4. Then query context for each sub-task as you implement
Example workflow:
1. User: "Implement OAuth integration"
2. You: rlm_plan("Implement OAuth integration", max_tokens=16000)
3. Result: Sub-queries with execution order
4. You: Implement each sub-query with rlm_context_queryFrom Snipara/snipara-claude, MIT.
More from Snipara/snipara-claude
- 0.565score
connect
Snipara
Connect Snipara Hosted MCP, check the configured project and diagnose account access.
SkillAFreshness: AClaude Code +9 - 0.565score
orchestrator
Snipara
Use Snipara Orchestrator for explicit controller plans, task coordination, execution receipts and proof gates.
SkillAFreshness: AClaude Code +9 - 0.561score
snipara
Snipara
Retrieve sourced project context and reviewed memory through Snipara Hosted MCP.
SkillAFreshness: AClaude Code +9 - 0.561score
companion
Snipara
Use Snipara Companion for local coding workflow plans, checkpoints, evidence and resuming saved work.
SkillAFreshness: AClaude Code +9 - 0.560score
settings
Snipara
Configure the Snipara plugin project and independently enable or disable Snipara, Companion and Orchestrator.
SkillAFreshness: AClaude Code +9 - 0.409score
orchestrate
Snipara
Perform multi-round context exploration when a simple query isn't sufficient.
SkillDFreshness: DClaude Code +9 - 0.409score
execute-code
Snipara
Execute code safely using RLM Runtime with Docker isolation when you need to run tests, validate implementations, or execute complex computations.
SkillDFreshness: DClaude Code +9 - 0.406score
chunk-implement
Snipara
Implement complex features by breaking them into chunks, querying Snipara for context, and using RLM Runtime for safe execution of each chunk.
SkillDFreshness: DClaude Code +9 - 0.405score
recall-context
Snipara
Recall previous context, decisions, or learnings from past interactions.
SkillDFreshness: DClaude Code +9 - 0.402score
query-docs
Snipara
Query Snipara documentation when you need context about the codebase, APIs, architecture, or implementation details.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jan 29, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Snipara/snipara-claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Snipara
- 0.582score
Snipara Project Intelligence
Snipara
Hosted MCP for source-backed project context, memory, code impact, and agent workflow continuity.
ConnectorAFreshness: ARemoteClaude Code +3 - 0.565score
orchestrator
Snipara
Use Snipara Orchestrator for explicit controller plans, task coordination, execution receipts and proof gates.
SkillAFreshness: AClaude Code +9 - 0.565score
connect
Snipara
Connect Snipara Hosted MCP, check the configured project and diagnose account access.
SkillAFreshness: AClaude Code +9 - 0.561score
snipara
Snipara
Retrieve sourced project context and reviewed memory through Snipara Hosted MCP.
SkillAFreshness: AClaude Code +9 - 0.561score
companion
Snipara
Use Snipara Companion for local coding workflow plans, checkpoints, evidence and resuming saved work.
SkillAFreshness: AClaude Code +9 - 0.560score
settings
Snipara
Configure the Snipara plugin project and independently enable or disable Snipara, Companion and Orchestrator.
SkillAFreshness: AClaude Code +9
Cite this page
plan-task skill. Agent Mart. https://agentmart.dev/skills/snipara-plan-task (last updated 2026-10-24)