estimate-spec

Add complexity estimates to existing spec file.

Command for Claude Code

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 commands/jnarowski/agentcmd/estimate-spec
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,930 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00007 $0.01930
Opus 5 $0.00003 $0.00965
Sonnet 5 $0.00001 $0.00386
Haiku 4.5 $0.00001 $0.00193

Measured today against content hash f46162d24fc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

estimate-spec 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 today.

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.

.claude/commands/estimate-spec.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Estimate Spec Complexity

Analyze an existing spec file and add/update complexity estimates for all tasks and phases.

Variables

  • $specIdentifier: $1 (required) - One of:
    • Spec ID (e.g., ef3)
    • Full path (e.g., .agent/specs/todo/ef3-auth-improvements-spec.md)
    • Feature name (e.g., auth-improvements)

Instructions

  • IMPORTANT: Use your reasoning model - THINK HARD about task complexity based on context needs
  • Locate the spec file from the provided identifier
  • Read and parse the existing spec (supports markdown and json formats)
  • Analyze each task and assign complexity score (1-10) based on context requirements
  • Calculate phase totals and average complexity
  • Update the spec file with complexity data while preserving all existing content
  • Can be run multiple times to re-estimate if complexity scores already exist
  • DO NOT include hour-based estimates - use complexity points only

Complexity Scale (Context-Focused)

Assign complexity based on context window usage and cognitive load, not time:

  • 1-2/10: Trivial - Single file, <50 lines changed, minimal context (config, doc, simple type)
  • 3-4/10: Simple - Few files, straightforward logic, low context (single endpoint, basic component)
  • 5-6/10: Moderate - Multiple related files, moderate context (DB field + migration + API update)
  • 7-8/10: Complex - Cross-cutting change, high context, multiple domains (full-stack feature, state refactor)
  • 9-10/10: Very complex - Architectural change, deep codebase knowledge required (major refactor, complex integration)

Key principle: Higher complexity = more context the agent needs to load and understand

Workflow

  1. Locate Spec File:
    • If $specIdentifier is a full path (contains /):
      • Use that path directly
    • Otherwise, look up in .agent/specs/index.json:
      • For numeric ID: Match by id field
      • For feature name: Fuzzy match folder name (e.g., message-queue matches ef3-message-queue-implementation/spec.md)
      • Use path from index: .agent/specs/{path}
    • If not found in index.json, fallback to directory search:
      • Search in order: .agent/specs/backlog/, .agent/specs/todo/, .agent/specs/done/
      • For ID: Pattern {id}-*/spec.{md,json}
      • For feature name: Pattern *{feature-name}*/spec.{md,json} (fuzzy match)
    • If still not found, report error

Read the full file on GitHub · 237 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. today First seen · 237 lines · 7 tokens per session scan A f46162d24fc0

Subscribe to this mod's changes

estimate-spec is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 7 tokens to every session and 1,930 once invoked, about $0.0000 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 2026-09-01.