decision-log

decision-log is a skill for Claude Code from danweinerdev/claude-sdd-planner. It costs 67 tokens per session (642 once invoked), scanned A, a copy of sdd-decision-log, MIT.

A rule for saving important project decisions in a shared decision log. It records choices that should remain true even after the current document is gone.

In plain words
What is it for?
Use it when someone makes or reverses a design choice, defines a project term, or answers a design question. It can capture and preserve those decisions for future work.
Why use it?
It prevents architectural choices from being forgotten, duplicated, or contradicted later. It also helps detect when a new choice conflicts with an earlier one.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the sdd-planner plugin — 34 skills, 8 agents shipped together

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/danweinerdev/claude-sdd-planner/decision-log
Any agent
npx skills add danweinerdev/claude-sdd-planner --skill decision-log
Clone the repo
git clone --depth 1 https://github.com/danweinerdev/claude-sdd-planner

Made for: Claude Code.

Or install sdd-planner, the plugin that ships this one along with the rest of its 34 skills, 8 agents.

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-log

README.md
[![agentmods](https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/decision-log.svg)](https://agentmods.dev/skills/danweinerdev/claude-sdd-planner/decision-log)
Your own site
<a href="https://agentmods.dev/skills/danweinerdev/claude-sdd-planner/decision-log"><img src="https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/decision-log.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 642 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod 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 $0.00067 $0.00642
Opus 5 $0.00034 $0.00321
Sonnet 5 $0.00013 $0.00128
Haiku 4.5 $0.00007 $0.00064

Measured 5d ago against content hash 0bf301c2885f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

decision-log 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.

Origin

This is a copy

98% identical to sdd-decision-log — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/decision-log/SKILL.md · 23 lines

How it starts

The opening of the file, as written. The whole thing — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision Log — Capture and Collision Discipline

The full convention (entry schema, lifecycle rules, collision procedure, distribution rules) lives in shared/decision-log.md in the plugin directory — read it before your first ledger write of a session. This skill exists so decision moments outside the lifecycle skills still reach the ledger.

Resolve the ledger per shared/decision-log.md § Ledger location — <planning-root>/Decisions/decisions.md for an in-repo planning root, <repo-root>/DECISIONS.md when the planning root is external (decisions live with the repo they represent). Create it from shared/templates/decision-log.md if missing.

When the user just decided something

  1. Recognize the moment: a stated choice between alternatives, a definition of a project term, an answer to a design question, or an explicit reversal. Then apply the admission test (shared/decision-log.md § Capture) before writing anything: the truth has to outlive the document being worked on, not already be carried by that document, and have had a real alternative that lost. Status updates, task events, one-off dispositions, and choices that a spec or design already states in full are not ledger entries — leaving them where they are is the correct outcome, not a miss.
  2. Run the collision check first (shared/decision-log.md § Collision Detection): grep the ledger for the new entry's tags, scope, and key nouns; apply the structural checks; judge survivors. On contradicts/supersedes → STOP and present both entries for the user to reconcile. Never auto-resolve, never pick by recency.
  3. Draft the entry (next sequential D-NNNN, decided_by: user only if the user actually stated the choice — otherwise status: proposed) and show the exact, complete entry text to the user for explicit approval before writing anything. The ledger is never edited without that approval — the decision being the user's does not make the write approved, and non-objection is not approval. If the user amends the entry, show the amended text and get approval again.
  4. Only after explicit approval: append the approved text verbatim, update the ledger's updated date, and confirm the frontmatter still parses as YAML. Confirm in one line (e.g., "Recorded as D-0007 in the decision ledger").

Read the full file on GitHub · 23 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 · 23 lines · 67 tokens per session scan A 0bf301c2885f

Subscribe to this mod's changes

decision-log is a skill published in the GitHub repository danweinerdev/claude-sdd-planner (2 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 642 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to sdd-decision-log, differing in 2 lines, and is treated as a copy.