task-triage

task-triage is a skill for Claude Code, Codex from BuildrAI/Buildr. It costs 47 tokens per session (3,674 once invoked), scanned A, original, MIT.

A task decision guide for determining whether a requested change belongs in code, current project knowledge, or an OpenSpec Change. An OpenSpec Change is a tracked proposal for changing a system's documented behavior.

In plain words
What is it for?
Use it to inspect the relevant facts, identify the source that defines the behavior, and hand the work to the right implementation or specification process.
Why use it?
It prevents changes from being made in the wrong place when specifications, implementation, tests, or permissions are unclear.

Skill for Claude CodeCodex

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/buildrai/buildr/task-triage
Any agent
npx skills add BuildrAI/Buildr --skill task-triage
Clone the repo
git clone --depth 1 https://github.com/BuildrAI/Buildr

Made for: Claude Code, Codex.

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 task-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/buildrai/buildr/task-triage.svg)](https://agentmods.dev/skills/buildrai/buildr/task-triage)
Your own site
<a href="https://agentmods.dev/skills/buildrai/buildr/task-triage"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/task-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.03674
Opus 5 $0.00023 $0.01837
Sonnet 5 $0.00009 $0.00735
Haiku 4.5 $0.00005 $0.00367

Measured yesterday against content hash 78ca4cfd3a42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-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 yesterday.

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.

projects/product/services/buildr/resources/workspace/skills/buildr/task-triage/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Triage Skill

本 Skill 只核对任务事实、作出正交决策并交接专业动作;不复制 Task Environment、OpenSpec 或验证手册,也不建立确定性路由器。

1. 核对任务事实

只读任务相关范围,不做全量审计。确认:

  • 用户希望外部行为或长期事实如何变化;
  • 相关 canonical specs、current knowledge、active Changes、实现、测试与 registries,以及其中的事实 authority;
  • 完整 Git repository set,使用 Workspace/Project/Service selector,不按目录层级猜测边界;
  • 写入授权、不可逆影响和仍需用户决定的语义冲突。

首次修改 proposal、Skill、代码、测试或当前知识前,从直接相关的 canonical specs、current knowledge、实现、测试与 registries 建立一次有界 authority source map。该 map 只用于当前 Agent 工作上下文,不写入 Task Record、Development Receipt、sidecar 或其他产品 authority;后续只有 scope、authority 或相关事实变化时才增量刷新,不反复全量扫描。

authority 冲突、授权或 repository set 不明、不可逆行为缺少决定,或是否进入实现仍未知时,停止对应写入,只询问会改变长期语义、责任边界或授权的最少问题。

UI Prototype 选择

若当前 Task、提案或预期实现可能产生用户可见的前端 UI 变化,向用户询问:“本次是否需要先生成界面原型(UI Prototype)?”询问只负责取得选择,不生成文件,也不改变语义治理或执行形态判断。

只有用户在当前任务中明确确认需要,才在方案已有足够上下文、正式前端实现开始前加载 selected ui-prototype Skill。用户拒绝、未确认或直接要求继续时不调用 Skill,正常推进后续流程;不得创建占位文件、waiver、Result、Receipt 或 blocker。UI Prototype 不替代 OpenSpec Change、Planning Review 或正式实现。一旦当前 Task 已生成原型,除非用户明确要求忽略,后续 Agent 必须在正式前端编辑前读取全部相关原型并按其信息架构、布局和交互开发。

2. 两轴决策

语义治理

选择 判定 动作
code-only canonical spec 已覆盖目标,且修改不改变可观察契约 不创建 Change
spec-maintenance specs、实现、registries 或已确认决定已证明当前事实,只需文档追上事实 不补造 Change;current knowledge 使用 maintain
change-flow 改变 SHALL/MUST、API、状态流、权限、业务规则、数据语义、兼容性或其他可观察承诺 一个独立业务目标一个 Change
blocked authority、业务语义或授权无法确认 报告冲突和最少决策问题

工程细节默认不进入 OpenSpec;但默认值、存储或内部机制一旦改变外部行为、数据含义、兼容性、安全边界或业务承诺,仍走 change-flow。不得用 spec-maintenance 绕过新需求评审,也不得用 code-only 掩盖规范缺失或事实不明。

若任务改变依赖、构建或测试入口,先把已确认Task scope与变更事实交给declaration-intake做只读差异检查;长期preparation.yml/verification.yml写入仍需用户确认并由各owner Skill完成。Triage不直接维护声明。

执行形态

  • implementation:修改代码、运行构建/测试,或需要长期开发上下文。
  • metadata-only:仅维护 OpenSpec artifacts、Rules、Skills、文档或模板,不进入代码、构建或测试。
  • unknown:信息不足;先澄清,不提前写 Change artifacts 或当前事实。

该轴独立于语义治理。Formal Task Record本身不是编辑、构建或有界测试的通用工作许可:用户授权、repository/ref、owned scope与副作用边界均明确时,Agent可以直接工作,但不得把该路径冒充ready Environment、Development、Formal Verification、Candidate、Finish或cleanup事实。选择Buildr-managed checkout、Preparation、runtime projection、持久资源、正式环境证据或自动Finish时,才必须根据Task完整Project/Service scope与Project preparation.yml形成Environment Plan并取得ready;metadata-only受管执行可以使用共享执行根。

Read the full file on GitHub · 115 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. yesterday Changed · -14 lines 78ca4cfd3a42
  2. 5d ago First seen · 129 lines · 47 tokens per session scan A a8f88ebcc38f

Subscribe to this mod's changes

task-triage is a skill published in the GitHub repository BuildrAI/Buildr (24 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 3,674 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

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

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