decision-journal

decision-journal is a skill for Claude Code from synaptiai/synapti-marketplace. It costs 68 tokens per session (3,263 once invoked), scanned A, original, Apache-2.0.

A decision log for AI-assisted development that records important choices found in code changes and flags changes that need human approval.

In plain words
What is it for?
Use it to start a log, extract decisions from a completed code difference, check for approval gates, or create a short summary for a pull request (a request to merge code).
Why use it?
AI work can make decisions that are hard to see later. This creates a record for review and highlights changes such as adding a dependency or changing security-sensitive code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

Part of the gh-workflow plugin — 4 skills, 5 commands shipped together

Good fit Use it to start a log, extract decisions from a completed code difference, check for approval gates, or create a short summary for a pull request (a request to merge code).

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synaptiai/synapti-marketplace/decision-journal
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 synaptiai/synapti-marketplace --skill decision-journal
Clone the repo
git clone --depth 1 https://github.com/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install gh-workflow, the plugin that ships this one along with the rest of its 4 skills, 5 commands.

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-journal

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/decision-journal/github.svg)](https://agentmods.dev/skills/synaptiai/synapti-marketplace/decision-journal)
Your own site
<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/decision-journal"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/decision-journal/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 decision-journal

Your own site · 80×15
<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/decision-journal"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/decision-journal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,263 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00068 $0.03263
Opus 5 $0.00034 $0.01631
Sonnet 5 $0.00014 $0.00653
Haiku 4.5 $0.00007 $0.00326

Measured 2d ago against content hash a0fa02d611ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

decision-journal scanned grade A with 1 finding 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 2d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

[ -z "$JOURNAL_DIR" ] && JOURNAL_DIR=$(jq -r '.journal.dir // empty' "$HOME/.claude/settings.gh-workflow.json" 2>/dev/null)

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/gh-workflow/skills/decision-journal/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision Journal

Captures, structures, and persists significant decisions made during AI-driven workflow execution. Uses post-hoc extraction from diffs rather than AI self-reporting during execution.

Purpose

In a fully AI-driven workflow, decisions happen invisibly. This skill makes them visible by:

  • Extracting decisions from completed diffs (what changed vs. what was expected)
  • Detecting high-stakes changes that warrant human approval (gates)
  • Structuring decisions into a machine-parseable journal format
  • Condensing journals into PR-body-ready summaries

Mode Routing

This skill operates in one of three modes. The calling command specifies the mode in its invocation prompt.

Mode When Used What It Does
init gh-start after branch creation Creates journal file header
log gh-start, gh-commit, gh-address after changes Extracts decisions from diff + evaluates gate triggers
summarize gh-pr during PR content generation Condenses journal for PR body

Read the mode from the invocation prompt and execute only that mode's instructions. If the mode is not one of init, log, or summarize, return an error: "Unknown mode: {mode}. Expected one of: init, log, summarize."

Mode: init

Input (from invocation prompt): Issue number, branch name, issue title, issue body.

Process:

Step 1: Read Configuration

# Read journal directory from settings (local > project > user > default)
JOURNAL_DIR=$(jq -r '.journal.dir // empty' .claude/settings.gh-workflow.local.json 2>/dev/null)
[ -z "$JOURNAL_DIR" ] && JOURNAL_DIR=$(jq -r '.journal.dir // empty' .claude/settings.gh-workflow.json 2>/dev/null)
[ -z "$JOURNAL_DIR" ] && JOURNAL_DIR=$(jq -r '.journal.dir // empty' "$HOME/.claude/settings.gh-workflow.json" 2>/dev/null)
[ -z "$JOURNAL_DIR" ] && JOURNAL_DIR=".decisions"
echo "Journal directory: $JOURNAL_DIR"

Step 2: Generate Header

Generate the journal file header:

# Decision Journal: Issue #{N} — {issue title}

**Issue**: #{N}
**Branch**: {branch-name}
**Started**: {YYYY-MM-DD}

---

Read the full file on GitHub · 322 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. 2d ago First seen · 322 lines · 68 tokens per session scan A a0fa02d611ef

Subscribe to this mod's changes

decision-journal is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 3,263 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.