A feature-triage tool that turns an idea into a versioned specification document. Triage means clarifying a request, checking whether it is ready, and recording the decisions needed before implementation.

It records the original request, investigates the project when needed, adds a plain-language readiness review, assigns an identifier, and updates the feature's status.

It exposes missing information and assumptions before coding begins, giving the team a shared description of what is ready to build.

triage — Skill for Claude Code by fledgeling-co/fledgeling-plugins

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 fledgeling-co/fledgeling-plugins --skill triage

Clone the repo

git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Or install shipyard, the plugin that ships this one along with the rest of its 8 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/triage/github.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/triage)

Your own site

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/triage"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/triage"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 228 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,065 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.00228	$0.03065
Opus 5.5	$0.00091	$0.01226
Sonnet 5.5	$0.00046	$0.00613
Haiku 4.5	$0.00023	$0.00307

Measured 1mo ago against content hash aaefc8e6c239, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

triage scanned grade B 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 1mo 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 directoriesmediumAgent snooping

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

Full mechanics — the availability check, the verbatim prompt contract (R1), how to dispose of findings, and the fallback rules — are in `feature-spec-pipeline/skills/work/references/codex-cli.md`. Follow it; don't re-der

plugins/shipyard/evals/baseline/triage-SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Triage (markdown specs)

Triage a feature idea for implementation-readiness and record it as a versioned spec document. The output is a short, non-technical product review appended to a spec markdown file plus a status change — never an implementation spec (that's the /plan skill's job).

This skill runs in your current session using Read/Glob/Grep/Write/Edit and the Workflow tool. It uses no issue-tracker MCP (Diolog Tasks or otherwise) and invokes no Agent SDK script — the spec markdown file is the single source of truth, replacing a tracker issue + comment thread.

Inputs

A feature description — inline text, or a path to a markdown/text file describing the feature; this becomes a brand-new spec.
Or an existing spec id (DIO-0001) to re-triage — read docs/specs/spec-DIO-0001.md and incorporate any answers/edits the human added since the last pass.
Optional --dry-run intent: investigate and report what you'd write, but make no file changes.

Procedure

Decide the mode.
- If the input is an id that resolves to an existing docs/specs/spec-<ID>.md, this is a re-triage: read that file in full — the original ## Feature description, every prior ## Triage section, and any answers/edits the human added. Human answers are authoritative — never re-ask an answered question.
- Otherwise it's a new feature: the input (inline text, or the file you read) is the original feature description. Allocate an id and create the spec (step 2).
Allocate an id and create the spec (new features only). Follow the exact id-allocation algorithm in references/spec-format.md (read docs/feature-specs/LEDGER.md; if it's missing, ask the user for the 3-letter project code — suggest one derived from the project/folder name, e.g. motif → MOT — then create the ledger). Allocate the next zero-padded id (e.g. DIO-0001), update the ledger's counter and table, and write docs/specs/spec-<ID>.md using the spec scaffold in references/spec-format.md — its ## Feature description section holds the original details verbatim. Set Status: Triage.

Read the full file on GitHub · 77 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.

1mo ago First seen · 77 lines · 228 tokens per session scan B aaefc8e6c239

Subscribe to this mod's changes

triage is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 228 tokens to every session and 3,065 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Planning

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

triage