log-decision

log-decision is a skill for Claude Code, Codex from chacosoldier/compabob. It costs 44 tokens per session (370 once invoked), scanned A, original, MIT.

A record of an important decision, including its reasoning, alternatives, expected result, and review date. It saves the record as a dated Markdown file in a decisions folder.

In plain words
What is it for?
Use it after a significant technical or strategic choice, including the option to do nothing. You can later review decisions whose planned review date has passed.
Why use it?
It prevents the reasons behind a choice from being lost or rewritten after the outcome is known. A later review makes it possible to compare expectations with what happened.

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/chacosoldier/compabob/log-decision
Any agent
npx skills add chacosoldier/compabob --skill log-decision
Clone the repo
git clone --depth 1 https://github.com/chacosoldier/compabob

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-decision

README.md
[![agentmods](https://agentmods.dev/badge/skills/chacosoldier/compabob/log-decision.svg)](https://agentmods.dev/skills/chacosoldier/compabob/log-decision)
Your own site
<a href="https://agentmods.dev/skills/chacosoldier/compabob/log-decision"><img src="https://agentmods.dev/badge/skills/chacosoldier/compabob/log-decision.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 370 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 $0.00044 $0.00370
Opus 5 $0.00022 $0.00185
Sonnet 5 $0.00009 $0.00074
Haiku 4.5 $0.00004 $0.00037

Measured 5d ago against content hash 63cb9867265e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

log-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 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.

.claude/skills/log-decision/SKILL.md · 46 lines

What it actually says

Log Decision

Capture a decision while the reasoning is fresh, so it can be reviewed honestly later. The point is calibration: a decision logged with its expected outcome can be checked against what actually happened.

Steps

  1. Gather the decision: what was decided, when, and by whom.
  2. Capture the reasoning: the key factors, and the single most important one.
  3. Capture the alternatives: what else was on the table, and why it lost. "Do nothing" counts.
  4. State the expected outcome and a review date (usually 30 to 90 days out).
  5. Write to vault/Decisions/YYYY-MM-DD-<slug>.md.

Format

---
title: [decision]
date: YYYY-MM-DD
review_on: YYYY-MM-DD
status: open
tags: [decision]
---

# [Decision]

**Decision**: [what was decided]

**Why**: [the reasoning, most important factor first]

**Alternatives considered**:
- [option] — rejected because [...]

**Expected outcome**: [what success looks like, concretely]

**Review on <review-date>**: _(left blank until the review)_

Reviewing

When /log-decision review is run, list decisions whose review_on date has passed, and for each ask: did it work out? Fill in the review section and set status to validated, mixed, or wrong. Honest reviews are the whole value.

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 · 46 lines · 44 tokens per session scan A 63cb9867265e

Subscribe to this mod's changes

log-decision is a skill published in the GitHub repository chacosoldier/compabob (32 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 370 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 2026-08-30.