decision-capture

decision-capture is a skill for Claude Code, Codex from suyoumo/ClawProBench. It costs 20 tokens per session (980 once invoked), scanned A, original, Apache-2.0.

A conversation skill that finds firm decisions and writes them down with the reasons, alternatives, and later results.

In plain words
What is it for?
Use it to track architecture, product, or project decisions and any follow-up commitments.
Why use it?
It prevents important choices from being lost in chat and keeps the reasoning behind them available for future review.

Skill for Claude CodeCodex

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 skills/suyoumo/clawprobench/decision-capture
Any agent
npx skills add suyoumo/ClawProBench --skill decision-capture
Clone the repo
git clone --depth 1 https://github.com/suyoumo/ClawProBench

Made for: Claude Code, Codex.

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 decision-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/suyoumo/clawprobench/decision-capture.svg)](https://agentmods.dev/skills/suyoumo/clawprobench/decision-capture)
Your own site
<a href="https://agentmods.dev/skills/suyoumo/clawprobench/decision-capture"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/decision-capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 980 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 $0.00020 $0.00980
Opus 5 $0.00010 $0.00490
Sonnet 5 $0.00004 $0.00196
Haiku 4.5 $0.00002 $0.00098

Measured 5d ago against content hash 089ad425a13e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decision-capture 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.

ironclaw/skills/decision-capture/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision Capture

When a decision is detected in conversation, record it in the commitments workspace. Decisions are durable knowledge — they explain why a path was chosen and enable outcome tracking over time.

Detection

Look for explicit decision language:

  • "We decided to..." / "I'm going with..." / "Let's do X"
  • "The call is..." / "We settled on..."
  • "I chose X over Y because..."

Do NOT capture:

  • Brainstorming or hypotheticals: "maybe we should...", "what if we..."
  • Preferences without commitment: "I think X is better"
  • Questions: "should we go with X?"

When uncertain, ask: "Was that a decision, or still thinking it through?"

Recording

This skill is only successful if the decision is actually persisted. Do not just summarize or acknowledge the decision.

Execution order is mandatory:

  1. Call memory_write for projects/commitments/decisions/<date>-<slug>.md
  2. If applicable, call memory_write for a follow-on commitment in projects/commitments/open/
  3. If applicable, call memory_write for context/intel/<slug>.md
  4. Only then confirm to the user what was recorded

Never say a decision was "captured", "recorded", or "saved" unless the corresponding memory_write call succeeded.

Write to projects/commitments/decisions/<date>-<slug>.md via memory_write:

---
type: decision
decided_at: <today YYYY-MM-DD>
context: <topic-slug>
participants: [<who was involved>]
confidence: <high if explicit, medium if inferred>
reversible: <true|false>
outcome: null
outcome_positive: null
tags: [<relevant tags>]
---
# <What was decided>

## Context
<Why this decision was needed — 1-2 sentences.>

## Options considered
1. **<Option A>** — <brief pros/cons>
2. **<Option B>** — <brief pros/cons>

## Rationale
<Why this option was chosen.>

## Outcome
<To be filled in later when outcome is known.>

Follow-through

  1. If the decision creates an obligation (e.g., "we decided to migrate by Q2"), also create a commitment in projects/commitments/open/ following the commitment schema.
  2. Write an intelligence MemoryDoc to context/intel/<slug>.md with a brief summary: "Decided X on . Rationale: ." This makes the decision searchable as durable knowledge.

Read the full file on GitHub · 124 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 · 124 lines · 20 tokens per session scan A 089ad425a13e

Subscribe to this mod's changes

decision-capture is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 10d ago), licensed Apache-2.0. It adds 20 tokens to every session and 980 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 2026-08-30.

Related

Other skills, from other repositories

Evaluation

Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.

agentic-in/elephant-agent · 25 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

agenthub-models

Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.

Prism-Shadow/penguin-harness · 37 tokens

benchmark-design

Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.

Prism-Shadow/penguin-harness · 22 tokens

remote-claude-code

Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…

Prism-Shadow/penguin-harness · 107 tokens

penguin-harness-dev

Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on…

Prism-Shadow/penguin-harness · 119 tokens