decision-triage

decision-triage is a skill for Claude Code from ninthwave-io/ninthwave. It costs 138 tokens per session (5,542 once invoked), scanned A, original, Apache-2.0.

An interactive process for reviewing decision logs stored in a .ninthwave/decisions/ folder and deciding what should happen to each one.

In plain words
What is it for?
Use it to ratify, revise, merge, skip, document, or create work items from decisions, with a human choosing the outcome each time.
Why use it?
It turns past choices into documented policy, architectural records, or follow-up work instead of leaving them as unresolved notes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Good fit Use it to ratify, revise, merge, skip, document, or create work items from decisions, with a human choosing the outcome each time.

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

Made for: Claude Code.

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-triage

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ninthwave-io/ninthwave/decision-triage"><img src="https://agentmods.dev/badge/skills/ninthwave-io/ninthwave/decision-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,542 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 $0.00138 $0.05542
Opus 5 $0.00069 $0.02771
Sonnet 5 $0.00028 $0.01108
Haiku 4.5 $0.00014 $0.00554

Measured 9d ago against content hash eddcec346102, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

decision-triage 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 9d 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.

skills/decision-triage/SKILL.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What this skill is

This is the canonical way to process decision logs in this repo (and any other repo that uses ninthwave). It is a synchronous, human-in-the-loop session: you read each log, the user decides what to do, you execute, you delete. There is a parallel async path (nw review-inbox decisions) that opens a weekly review PR; this skill is the sit-down-and-clear-it-now alternative.

Decision logs are not the same as friction logs. A friction log says "something hurt, fix it or drop it." A decision log says "I made a choice X for reason Y, and here is what shipped." So the central question is not "fix or drop" but ratify, codify, or follow up: is the choice sound, should it be promoted into durable policy or recorded as a permanent architectural record, and does it leave behind a tradeoff or missing guardrail that needs its own work item?


Repo-agnostic rule (read before anything else)

This skill ships from one repo but runs in any repo that uses ninthwave. The only paths and contracts you may assume exist are the ones ninthwave itself defines:

  • .ninthwave/decisions/ -- the inbox to drain
  • .ninthwave/work/ -- where new work items get written
  • .ninthwave/work-item-format.md -- work item shape
  • nw lineage-token -- CLI for lineage IDs
  • The decision file fields: item, date, summary, context, decision, rationale

Anything outside .ninthwave/ is consuming-repo-specific and must be discovered at runtime. That includes docs/, agents/, skills/, CLAUDE.md, README.md, ADR directories, technical guides, and so on. Do not hardcode these paths anywhere in this session. Phase 2 subagents are responsible for discovering each repo's actual conventions before recommending where a CODIFY edit or an ADR record should land. If you find yourself about to suggest editing a file you have not opened, stop and re-survey.


Interactive Questions (CRITICAL)

This skill is highly interactive. You MUST use your interactive question tool to ask the user questions. Do NOT print a question as text and wait for a response.

Read the full file on GitHub · 336 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. 9d ago First seen · 336 lines · 138 tokens per session scan A eddcec346102

Subscribe to this mod's changes

decision-triage is a skill published in the GitHub repository ninthwave-io/ninthwave (8 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 138 tokens to every session and 5,542 once invoked, about $0.0007 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 2026-08-31.