Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/pyrex41/skill-manager/create_plangit clone --depth 1 https://github.com/pyrex41/skill-managerWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00009 | $0.00746 |
| Opus 5 | $0.00005 | $0.00373 |
| Sonnet 5 | $0.00002 | $0.00149 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
create_plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Implementation Plan
You are tasked with creating a detailed, actionable implementation plan through collaborative research and iteration.
Philosophy
Be skeptical and thorough. Plans should:
- Eliminate all open questions before finalization
- Be based on deep understanding of the existing codebase
- Include both automated and manual success criteria
- Be iterative - seek feedback at each phase
Process
Phase 1: Context Gathering
- Read all mentioned files completely - Never use limit/offset, you need full context
- Spawn parallel research agents to understand the codebase:
- Use
codebase-locatorto find WHERE relevant code lives - Use
codebase-analyzerto understand HOW specific code works - Use
thoughts-locatorto find existing documentation
- Use
- Present your understanding with focused questions for clarification
Phase 2: Research & Discovery
- Verify any user corrections through new research
- Create a todo list to track exploration
- Spawn concurrent sub-tasks for comprehensive investigation
- Present findings with design options when multiple approaches exist
Phase 3: Plan Structure Development
- Propose phasing before detailed writing
- Seek feedback on organization and granularity
- Identify dependencies between phases
Phase 4: Detailed Plan Writing
Create a markdown document with this structure:
# Plan: [Feature/Task Name]
## Overview
[2-3 sentence summary of what this plan accomplishes]
## Current State Analysis
[What exists today, relevant code locations]
## Desired End State
[Clear description of the goal]
## Implementation Approach
[High-level strategy]
## Phases
### Phase 1: [Name]
**Goal**: [What this phase accomplishes]
**Changes**:
- [ ] Change 1 (`file:line`)
- [ ] Change 2 (`file:line`)
**Success Criteria - Automated**:
- [ ] `make check` passes
- [ ] `make test` passes
- [ ] Specific test case passes
**Success Criteria - Manual**:
- [ ] UI shows expected behavior
- [ ] Edge case X works correctly
### Phase 2: [Name]
[Continue pattern...]
## Open Questions
[MUST be empty before plan is finalized]
## Risks and Mitigations
[Known risks and how to handle them]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 122 lines · 9 tokens per session scan A de7c79090991
create_plan is a command published in the GitHub repository pyrex41/skill-manager (3 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 746 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.