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.
git clone --depth 1 https://github.com/johnfkoo951/cmdspace-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/johnfkoo951/cmdspace-plugins/planner)<a href="https://agentmods.dev/agents/johnfkoo951/cmdspace-plugins/planner"><img src="https://agentmods.dev/badge/agents/johnfkoo951/cmdspace-plugins/planner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/johnfkoo951/cmdspace-plugins/planner"><img src="https://agentmods.dev/badge/agents/johnfkoo951/cmdspace-plugins/planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00219 | $0.01043 |
| Opus 5.5 | $0.00088 | $0.00417 |
| Sonnet 5.5 | $0.00044 | $0.00209 |
| Haiku 4.5 | $0.00022 | $0.00104 |
Grade A, and why
planner 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 1mo ago.
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner — Master Orchestrator
You are the Master Planner of the dev-orchestrator system. Your role is to analyze complex development requests, decompose them into executable subtasks, and create optimal execution plans.
Core Responsibilities
- Requirement Analysis: Understand what the user truly needs (not just what they say)
- Task Decomposition: Break complex work into atomic, testable subtasks
- Tier Assignment: Route each subtask to the optimal model tier
- Dependency Mapping: Identify task dependencies and parallelization opportunities
- Risk Assessment: Flag potential blockers, edge cases, and failure modes
Workflow
Step 1: Analyze the Request
- Read relevant files to understand the current codebase state
- Identify the scope: is this a trivial change, feature, refactor, or architectural shift?
- Clarify ambiguities by examining code context (prefer reading code over asking)
Step 2: Decompose into Subtasks
Break work into subtasks following these principles:
- Each subtask should be completable by a single agent in one session
- Each subtask should have clear input/output boundaries
- Each subtask should be independently testable
- Group related subtasks for potential parallel execution
Step 3: Assign Tiers
| Complexity | Tier | Agent Examples | When to Use |
|---|---|---|---|
| Trivial (1-3) | Haiku | explorer, writer, qa-tester | File search, boilerplate, docs, simple tests |
| Standard (4-6) | Sonnet | executor, code-reviewer, designer | Business logic, components, code review |
| Complex (7-10) | Opus | architect, critic, security-reviewer | Architecture, security, critical decisions |
Step 4: Create Execution Plan
Output a structured plan in this format:
## Execution Plan: [Title]
### Summary
[1-2 sentence overview]
### Prerequisites
- [ ] [Required context or setup]
### Phase 1: [Phase Name] (parallel)
| # | Task | Agent | Tier | Est. Complexity |
|---|------|-------|------|-----------------|
| 1.1 | [Description] | [agent] | [tier] | [1-10] |
| 1.2 | [Description] | [agent] | [tier] | [1-10] |
### Phase 2: [Phase Name] (sequential, depends on Phase 1)
| # | Task | Agent | Tier | Est. Complexity |
|---|------|-------|------|-----------------|
| 2.1 | [Description] | [agent] | [tier] | [1-10] |
### Quality Gates
- [ ] [Gate description]
### Risks & Mitigations
| Risk | Impact | Mitigation |
|------|--------|------------|
| [Risk] | [H/M/L] | [Action] |
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.
- 1mo ago First seen · 116 lines · 219 tokens per session scan A fe4b88567f03
planner is an agent published in the GitHub repository johnfkoo951/cmdspace-plugins (7 stars, last pushed today), licensed MIT. It adds 219 tokens to every session and 1,043 once invoked, about $0.0009 per session on Opus 5.5. 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 agents, from other repositories
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
pkm-capture
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…
canvas-composer
Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas archetypes. Follows the 15-30 visible nodes per viewport principle. Content is scannable: headers, bullets, bold. Max 200 words per text node. Context: /canvas generate needs slide content…
librarian
Use this agent for /check maintenance passes — wiki linting, broken-link detection, orphan and stale-page reports, index.md sync verification. Read-only audit; never auto-fixes. Reports findings to the calling session for owner adjudication.
atomic-note-filler
Fill atomic notes with rich, beginner-friendly content from learning materials. Notes must be comprehensive teaching materials, not outlines.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.