log-a-decision

log-a-decision is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 58 tokens per session (1,412 once invoked), scanned A, original, MIT.

A decision record that documents the context, alternatives, trade-offs, choice, reasoning, and consequences. It can add the entry to a decision log from your description or meeting notes.

In plain words
What is it for?
Use it to record a team decision, review pending decisions, or turn meeting notes into an ADR-style entry. ADR means a written record of an architecture or other important decision.
Why use it?
It prevents important choices from being forgotten or repeatedly debated. It gives the team a shared record to refer to later.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to record a team decision, review pending decisions, or turn meeting notes into an ADR-style entry. ADR means a written record of an architecture or other important decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/log-a-decision
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.

Any agent
npx skills add akiotanaka847/qaio-desktop --skill log-a-decision
Clone the repo
git clone --depth 1 https://github.com/akiotanaka847/qaio-desktop

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 log-a-decision

README.md
[![agentmods](https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/log-a-decision/github.svg)](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/log-a-decision)
Your own site
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/log-a-decision"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/log-a-decision/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 log-a-decision

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/log-a-decision"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/log-a-decision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,412 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 $0.00058 $0.01412
Opus 5 $0.00029 $0.00706
Sonnet 5 $0.00012 $0.00282
Haiku 4.5 $0.00006 $0.00141

Measured 7d ago against content hash acc52226c108, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

log-a-decision 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 7d 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.

store/agents/operations/.agents/skills/log-a-decision/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Log A Decision

When to use

  • User says "we decided", "log the decision on", "capture that call", "ADR this".
  • Pasted/connected meeting notes contain clear decision pattern.
  • User asks review open decision backlog - skill also marks pending rows decided when user declares them.

Connections I need

I run external work through Composio. Before this skill runs I check the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.

  • Meeting recorder (Fireflies, Gong) - Optional. Lets me pull a transcript when you say "log the call we just had." If not connected I work from what you paste.
  • Docs / notes (Notion, Google Docs) - Optional. If you have a decision log or RACI doc elsewhere I read it before drafting.

This skill works without any connection. I never block here - worst case you describe the decision and I capture it.

Information I need

I read your operations context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.

  • The decision itself - Required. Why I need it: I'm capturing one specific call, not generating one. If missing I ask: "What did you decide, and what was on the table before you picked?"
  • Stakeholders and decider - Required. Why I need it: drives whether the row lands as pending or decided. If missing I ask: "Who decided this - you, a co-founder, the team - and is it final or still open?"
  • Decision rights / RACI - Optional. Why I need it: lets me default the right status without asking each time. If you don't have it I keep going with TBD and ask once: "Who owns calls like pricing, hiring, or product strategy? A sentence is fine."
  • Active priorities - Required. Why I need it: I tag whether the decision is load-bearing for what you're pushing on. If missing I ask: "What are the 2 to 3 things the company is pushing on this quarter?"

Read the full file on GitHub · 106 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. 7d ago First seen · 106 lines · 58 tokens per session scan A acc52226c108

Subscribe to this mod's changes

log-a-decision is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 1,412 once invoked, about $0.0003 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 2026-09-05.