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.
npx skills add ninthwave-io/ninthwave --skill decision-triagegit clone --depth 1 https://github.com/ninthwave-io/ninthwaveWrote 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.
[](https://agentmods.dev/skills/ninthwave-io/ninthwave/decision-triage)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 shapenw 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.
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.
- 9d ago First seen · 336 lines · 138 tokens per session scan A eddcec346102
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.
Other skills, from other repositories
armada-gate
Run an evidence-gate checklist for each success criterion in the current phase. Use when checking if a phase is complete before marking it passed.
armada-contract
Co-write an armada contract (REQUIREMENTS.md) one question at a time. Use when drafting or updating a feature contract before implementation.
armada-dispatch
Dispatch subagents in parallel with disjoint file scope. Use when facing 2+ independent tasks, multiple files, or parallel phases. Triggers on: parallelize, dispatch subagents, run in parallel.
armada-voyage-finish
Voyage-finalization ritual. Load at voyage end, dispatch a galleon subagent to rebase, fix TODO PR refs, regen scaffold, push, open/update PR. Triggers on: finish voyage, finalize, rebase, PR.
armada-ledger
Pick the right ledger for a finding. Use when writing defects, adversarial findings, or security findings. Triggers on: ledger, defect, adversarial, security finding, DEF-001, ADV-001, SEC-001.
armada-ponytail
Minimal, pragmatic code discipline for Clipper and Galleon. Laziest working solution, no fluff, no YAGNI bloat.