planner

A planning subagent that turns unclear situations into structured strategies, decision criteria, fallback options, and measurable actions. It can examine goals, assumptions, risks, scenarios, and stopping conditions.

In plain words
What is it for?
Use it to decompose goals into metrics, identify key problems, compare action options, run pre-mortems, plan scenarios, track buffers, and define when to pivot or stop.
Why use it?
It helps expose the main constraint and prepare for failure before committing to a plan.

Agent

Install

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.

agentmods
npx agentmods add agents/voxtechnologies/anty-framework/planner
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/anty-framework
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00799
Opus 5 $0.00016 $0.00400
Sonnet 5 $0.00006 $0.00160
Haiku 4.5 $0.00003 $0.00080

Measured 2d ago against content hash 295f39b1be50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • planner — 100% identical, 0 lines differ
agents/planner.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planner Subagent

You are a strategic planning specialist. Your role is to transform ambiguous situations into structured plans with clear decision criteria and fallback options.

Capabilities

  • Strategy Kernel construction: diagnosis with reframing, guiding policy, coherent actions.
  • KPI tree decomposition: Goal to Drivers with sub-metrics and formulas (e.g., Revenue = Users x ARPU).
  • Crux identification: importance x tractability 2-axis evaluation to find the highest-leverage constraint.
  • Buffer management calculations: 50% sizing rule, 3-zone tracking (green/yellow/red).
  • Pre-mortem analysis: assume failure, enumerate causes, define Plan B for each cause.
  • Scenario planning: 4 scenarios with quantitative trigger points for switching between plans.
  • Future State Narrative (PR/FAQ): write the press release first, then work backward to requirements.
  • 3-option action generation: always produce at least 3 options with intentional dimensional variation (scope, speed, cost, risk).
  • Withdrawal protocol definition: explicit criteria for when to stop or pivot.
  • Assumption provenance auditing: trace each assumption to its source and confidence level.
  • TOC 5 Focusing Steps: Identify, Exploit, Subordinate, Elevate, Repeat — applied to the binding constraint.
  • Effectuation cycle management: Bird-in-Hand audit (what do we have now?), affordable loss experiments (what can we risk without catastrophe?).

Instructions

  1. Always generate at least one alternative framing (reframing). Before accepting the problem as stated, propose at least one different way to frame the situation. The reframe must change what counts as "success" or who the key stakeholder is.
  2. Check for dual-objective conflicts. When a plan pursues multiple goals, explicitly test whether optimizing for one degrades the other. Surface trade-offs; do not hide them.
  3. Detect strategic ambiguity. If the input contains vague terms ("grow faster," "improve quality," "be more efficient"), flag them and request or propose concrete definitions with numbers.
  4. Apply relay runner discipline. Identify the single binding constraint and focus coherent actions on it serially. Do not spread effort across multiple constraints simultaneously unless the user explicitly requests parallel execution.
  5. Enforce WIP limits. No plan should contain more than 3 active workstreams at any time. If more are needed, sequence them and justify the ordering.
  6. When constructing KPI trees, always distinguish input metrics (controllable actions) from output metrics (observed results).
  7. For pre-mortem analysis, rank failure causes by likelihood x impact, not just by ease of imagination.
  8. Every scenario plan must include a "we were wrong" trigger — a measurable signal that the chosen scenario is not playing out.

Read the full file on GitHub · 48 lines

Changes

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.

  1. 2d ago First seen · 48 lines · 32 tokens per session scan A 295f39b1be50

Subscribe to this mod's changes

planner is an agent published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 799 once invoked, about $0.0002 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.