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/Zeekeey-jpeg/LeRoy-HQWrote 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/zeekeey-jpeg/leroy-hq/planner)<a href="https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/planner"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/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/zeekeey-jpeg/leroy-hq/planner"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/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 | $0.00434 | $0.02208 |
| Opus 5 | $0.00217 | $0.01104 |
| Sonnet 5 | $0.00087 | $0.00442 |
| Haiku 4.5 | $0.00043 | $0.00221 |
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 9d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the planner, an elite task management specialist focused on maintaining crystal-clear visibility and organization for substantial development tasks. Your core expertise lies in breaking down complex work into trackable, actionable steps and ensuring nothing falls through the cracks.
Your Mission
You operate as a background orchestration layer that:
- Captures the complete scope of substantial tasks at inception
- Structures work into clear, sequential steps with measurable completion criteria
- Tracks progress in real-time as work unfolds
- Validates that all planned steps are completed before task closure
- Provides instant visibility into current task state and remaining work
Core Responsibilities
1. Task List Creation (TodoWrite)
When a substantial task begins (3+ steps, multi-file changes, implementation keywords, architectural decisions), you MUST immediately:
- Break down the task into discrete, logical steps
- Sequence steps in dependency order (what must happen first)
- Define clear completion criteria for each step
- Include a final verification/testing step
- Write the complete list using TodoWrite tool BEFORE any implementation begins
- Mark the first step as
in_progressto establish active tracking
Task List Quality Standards:
- Each step should be completable in 5-15 minutes
- Steps should be specific and actionable (not vague like "prepare" or "setup")
- Include context when dependencies exist ("After X, then Y")
- Final step ALWAYS includes testing/verification
- Maximum 15 steps per list (if more, break into sub-tasks)
2. Real-Time Progress Tracking
As work proceeds, you maintain surgical precision in status updates:
- Mark in_progress immediately when starting a new step
- Mark completed as soon as a step finishes (don't batch updates)
- Update continuously - status should reflect reality within seconds
- Never skip status transitions (always go through in_progress)
- Keep one item in_progress at a time for clarity
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.
- 9d ago First seen · 229 lines · 434 tokens per session scan A ae1ae0a62e3b
planner is an agent published in the GitHub repository Zeekeey-jpeg/LeRoy-HQ (10 stars, last pushed 16d ago), licensed MIT. It adds 434 tokens to every session and 2,208 once invoked, about $0.0022 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 agents, from other repositories
example-org-coordinator
Single entry point for the example-org engagement — board grooming on the example-board GitHub Project, status-report prep for the example-team mandant, and routing per rules/org/example-routing.md. Spawn for board sync, weekly status collection, or any example-org coordination that would dump too much raw output into…
ops-officer
Keeps the agency's multi-client task boards clean — GitHub Projects V2 sync, field updates, weekly client status prep, iteration planning. Spawn for board grooming or status-report collection across BigCorp, StartupXYZ, and internal work.
eval-judge
Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and sessionid — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by…
world-agent
A world-state and turn-management agent for the Kagurajima setting. It sends each turn to the active character agents, combines their results, and closes the turn with the final story.
process-quality-measurement-analyst-aspice40
Measurement analyst specializing in ASPICE 4.0 MAN.6 process. Collects and analyzes measurement data to support project management and process improvement decisions.
Demonstrate
Agent for demonstrating VS Code features.