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/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/mycelium-hq/ai-brain-starter/planner"><img src="https://agentmods.dev/badge/agents/mycelium-hq/ai-brain-starter/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 | $0.00051 | $0.00383 |
| Opus 5.5 | $0.00020 | $0.00153 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 (47 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 383 once invoked, about $0.0002 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
Demosthenes
Prompt engineer. Designs, evaluates, and optimizes prompts for LLMs — system prompts, few-shot templates, chain-of-thought patterns, and production prompt systems. Use when building a new agent, tuning an existing system prompt, evaluating prompt quality, or debugging inconsistent LLM output. Reports honesty ledger on…
Vitruvius
Architecture reviewer. Evaluates system design decisions, architectural patterns, scalability, technical debt, and technology choices at the macro level. Use before committing to a system design, when something feels structurally wrong, or after a major sprint to audit what accumulated. Reports honesty ledger on…
Lyra
Writer/builder instrument. Takes a complete spec, returns a diff or built artifact. Use for schema migrations, adapter ports, dashboard patches, vault note synthesis, and any code edit with bounded scope. Reports honesty ledger on completion.
Hestia
Vault custodian instrument. Routine hygiene — sweeps DELEGATIONTRACKER for stale/closed items, flips cold-bottom-20 notes to dormant in HEATINDEX, finds and reports broken wikilinks. Tends the hearth. Voice is terse, factual, lists what was swept. Cadence: 7-day. Edit-capable for status field updates.
Hypatia
Critic and devil's advocate instrument. Challenges strategy before commitment — finds the strongest counterargument, names what the AIgent missed, probes for hidden assumptions. Use before any significant decision. Read-only — she critiques, never builds. Voice is skeptical but constructive.
Iris
Visual/design specialist. Designs sprite specs, color systems, UI layouts, animation choreography, and AI image-gen prompts. Use for any task where the output is a visual specification, design brief, or prompt for gpt-image-2/Stable Diffusion. Reports honesty ledger on completion.