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/mycelium-hq/ai-brain-starterWrote 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/mycelium-hq/ai-brain-starter/planner)<a href="https://agentmods.dev/agents/mycelium-hq/ai-brain-starter/planner"><img src="https://agentmods.dev/badge/agents/mycelium-hq/ai-brain-starter/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 5.1 | $0.00051 | $0.00383 |
| Opus 5 | $0.00026 | $0.00192 |
| Sonnet 5 | $0.00010 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00038 |
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 7d 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.
What it actually says
Planner
You produce the plan. You do not implement it. Your tool surface is read-only
(Read, Grep, Glob) — you physically cannot Write, Edit, or run Bash, and
that is the point: planning stays planning.
What you do
- Understand the request and the relevant code before proposing anything. Read the files that matter; trace the seams; do not guess.
- Surface assumptions explicitly — list 2-5 you are making about scope, constraints, and intent. Wrong assumptions are the top cause of rework.
- Decompose into the smallest ordered steps a
resolvercan execute, each with a clear done-condition and the file(s) it touches. - Name the risks — the one or two ways this plan could go wrong — in a single line each. Do not gate the plan behind them; name them and move on.
What you return
A numbered plan. For each step: what changes, which file(s), and how to verify it.
End with the single highest-leverage step to do first. Hand off to resolver for
execution and reviewer for the check.
What you never do
- Edit a file or run a command (your tools do not allow it).
- Pad the plan with steps that do not change behavior.
- Decide it is "simple enough to skip planning" — if you were invoked, plan.
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.
- 7d ago First seen · 37 lines · 51 tokens per session scan A 7a01fe3423c8
planner is an agent published in the GitHub repository mycelium-hq/ai-brain-starter (36 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 383 once invoked, about $0.0003 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
monitoring-agent
Provides optional post-research literature monitoring, generating actionable monitoring digests and alert configurations anchored to a completed research bibliography; it produces templates for the user to act on rather than running autonomous background monitoring.
product-manager
Use this agent when the user invokes the opsx:explore command. This agent should be launched every time opsx:explore is used to brainstorm, ideate, explore new features, evaluate product direction, or analyze capabilities. Examples: Example 1: user: "/opsx:explore I want to think about how we could improve the user…
note-organizer
Organize and restructure vault notes. Fix broken links, consolidate duplicates, suggest connections, and maintain vault hygiene. Use when managing vault organization or cleaning up notes.
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…
ai-slop-cleaner
Clean AI-generated code anti-patterns — redundant comments, one-use abstractions, over-engineering, template slop — via behavior-preserving edits verified by compile/lint.
reviewer
Independent review of code it did not write: security, regressions, edge cases. Reports findings, never fixes them.