estimate-point

estimate-point is a command for Claude Code from axiomantic/spellbook. It costs 22 tokens per session (2,230 once invoked), scanned A, original, MIT.

A multi-agent estimation step that assigns Fibonacci-style effort points to tickets and reconciles disagreements between independent estimates.

In plain words
What is it for?
Pointing tickets, comparing independent complexity assessments, and sending oversized work back for splitting.
Why use it?
It reduces anchoring between estimators and prevents very large or unclear work from being treated as a reliable single estimate.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions subagents; names the AskUserQuestion tool.

Good fit Pointing tickets, comparing independent complexity assessments, and sending oversized work back for splitting.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/estimate-point
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.

Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

Made for: Claude Code.

Wrote 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.

agentmods badge for estimate-point

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/estimate-point/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/estimate-point)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/estimate-point"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/estimate-point/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.

agentmods 80×15 button for estimate-point

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/estimate-point"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/estimate-point.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00022 $0.02230
Opus 5 $0.00011 $0.01115
Sonnet 5 $0.00004 $0.00446
Haiku 4.5 $0.00002 $0.00223

Measured 5d ago against content hash b21782e6609d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

estimate-point 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 5d 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.

commands/estimate-point.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Estimate Point (Phases 4-5)

Personas MUST be dispatched in parallel, never sequentially.

Invariant Principles

  1. Parallel dispatch protects independence: All personas point each ticket in one batched call; sequential dispatch lets later personas anchor on earlier numbers and collapses multi-agent consensus.
  2. Disagreement triggers reconciliation: Splits greater than 1 Fibonacci step mean someone is missing context — re-dispatch with cross-visible reasoning; on persistent disagreement take the higher value and flag it.
  3. 34 halts, never estimates: A consensus value of 34 stops the pipeline and loops back to scope for splitting before any multiplier or buffering runs.
  4. Conservative on ambiguity: When personas disagree on complexity, take the HIGHER classification; never apply M_AI < 1.0 to High-complexity work to flatter AI tooling.
  5. Consensus is synthesis, not voting: The output is the reconciled median of independent expert reasoning, never one persona's number with the others discarded as "wrong".

Read the full file on GitHub · 222 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. 5d ago First seen · 222 lines · 22 tokens per session scan A b21782e6609d

Subscribe to this mod's changes

estimate-point is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 2,230 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 2026-09-03.