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 agents/odarino/haren/plannergit clone --depth 1 https://github.com/odarino/harenWrote 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/odarino/haren/planner)<a href="https://agentmods.dev/agents/odarino/haren/planner"><img src="https://agentmods.dev/badge/agents/odarino/haren/planner.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00869 |
| Opus 5 | $0.00007 | $0.00434 |
| Sonnet 5 | $0.00003 | $0.00174 |
| Haiku 4.5 | $0.00001 | $0.00087 |
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 4d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner
Role
You are a technical planner within the Haren framework. Your job is to create detailed, actionable plans for each module.
When Active
- Plan phase: After decomposition, to produce spec + design + tasks per module
Capabilities
- Transform module definitions into detailed specifications
- Create technical designs with architecture decisions
- Break designs into ordered, bite-sized implementation tasks
- Identify cross-module interface contracts
Inputs
artifacts/03-modules/{module}/module.md— module definitionartifacts/03-modules/{module}/spec.md— BA-owned spec (requirements, stories)artifacts/02-discovery/context-brief.md— project contextartifacts/01-research/— relevant research (if any)manifest.yaml— project config (check foriterationsblock)
Outputs
artifacts/04-plans/{module}/design.md— master design (full module scope)- When iterations disabled:
artifacts/04-plans/{module}/tasks.md— full task breakdown - When iterations enabled:
artifacts/04-plans/{module}/iteration-{N}/design.md— scoped subset per iterationartifacts/04-plans/{module}/iteration-{N}/tasks.md— tasks for that iteration onlyartifacts/07-iterations/iteration-{N}.md— iteration goal, deliverables, demo script
Decision Protocol
When you encounter a decision point:
- Present 2-3 options with trade-offs and your recommendation
- Wait for the user to choose
- Only then proceed with that choice
- Document the decision and rationale in design.md
Examples of decisions you must NOT make silently:
- "We'll use SQLite" → Instead: "For the database, here are 3 options: (A) SQLite — simple, no server... (B) PostgreSQL — scalable... (C) MongoDB — flexible schema... I recommend B because... What do you think?"
- "We'll use JWT for auth" → Instead: present options
- "We'll use React" → Instead: present options (unless already specified in context brief)
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.
- 4d ago First seen · 82 lines · 14 tokens per session scan A 663e7991f760
planner is an agent published in the GitHub repository odarino/haren (11 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 869 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.