validate-workitem

validate-workitem is a skill for Claude Code, Codex from kohj1018/agentic-dev-harness. It costs 29 tokens per session (271 once invoked), scanned A, a copy of accept-milestone, MIT.

A workflow for checking one concrete implementation task before it is started or accepted. A work item is a defined piece of project work with its own requirements and outcome.

In plain words
What is it for?
Use it when you explicitly run $validate-workitem to review a work item against the project's documented process.
Why use it?
It helps catch unclear requirements, missing details, and problems with the task's proposed solution before coding or sign-off.

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/kohj1018/agentic-dev-harness/validate-workitem
Any agent
npx skills add kohj1018/agentic-dev-harness --skill validate-workitem
Clone the repo
git clone --depth 1 https://github.com/kohj1018/agentic-dev-harness

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 validate-workitem

README.md
[![agentmods](https://agentmods.dev/badge/skills/kohj1018/agentic-dev-harness/validate-workitem.svg)](https://agentmods.dev/skills/kohj1018/agentic-dev-harness/validate-workitem)
Your own site
<a href="https://agentmods.dev/skills/kohj1018/agentic-dev-harness/validate-workitem"><img src="https://agentmods.dev/badge/skills/kohj1018/agentic-dev-harness/validate-workitem.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 271 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 80% 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 $0.00029 $0.00271
Opus 5 $0.00015 $0.00135
Sonnet 5 $0.00006 $0.00054
Haiku 4.5 $0.00003 $0.00027

Measured 4d ago against content hash 3cc1055978ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-workitem 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 4d 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

80% identical to accept-milestone — 10 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.

.agents/skills/validate-workitem/SKILL.md · 15 lines

What it actually says

Source of truth: .claude/skills/validate-workitem/SKILL.md. Read it and follow the workflow.

Treat all frontmatter keys other than name and description (e.g., agent:, disable-model-invocation:, allowed-tools:, context:, argument-hint:, model:, effort:) as Claude-only and ignore them — execute locally in Codex.

Slash command translation: 본문 안의 /validate-workitem 표기는 Claude 슬래시 커맨드다. Codex에서는 $validate-workitem으로 읽고 사용자에게 안내한다 (예: 본문 "다음 단계: /finalize-workitem T-001" → Codex 응답에서는 "다음 단계: $finalize-workitem T-001"). Codex CLI는 /를 빌트인 슬래시 커맨드에 쓰므로 명시적 치환이 필요.

Preserve all repo policies from AGENTS.md and docs/.

If the source path no longer exists, this wrapper is stale — see ADR-010.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 15 lines · 29 tokens per session scan A 3cc1055978ec

Subscribe to this mod's changes

validate-workitem is a skill published in the GitHub repository kohj1018/agentic-dev-harness (2 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 271 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to accept-milestone, differing in 10 lines, and is treated as a copy.

Related

Other skills, from other repositories

sprint-testing

Orchestrates in-sprint manual QA per issue across Stages 1 (Planning), 2 (Execution) and 3 (Reporting). Use for user-story testing, bug retesting, and sprint-wide QA loops. Creates the PBI folder, drives session-start, runs the triage + veto + risk-score decision tree on bugs, produces the ATP + ATR + TC artifacts in…

upex-galaxy/agentic-qa-boilerplate · 213 tokens

shift-left-testing

Orchestrates pre-sprint Shift-Left QA on a batch of backlog Stories. Use when the user wants to refine acceptance criteria, surface ambiguities + gaps, draft an ATP outline, and hand off to PO/Dev BEFORE the Story enters a sprint — so defects are prevented in the requirements, not detected after implementation.…

upex-galaxy/agentic-qa-boilerplate · 303 tokens

acli

Atlassian CLI (official acli binary, v1.3+ as of 2026) for Jira Cloud, Confluence Cloud, and org admin tasks from the terminal. Use whenever the user wants to create, view, edit, transition, assign, clone, archive, comment on, link, or bulk-operate on Jira work items; list or manage projects, boards, sprints, filters…

upex-galaxy/agentic-qa-boilerplate · 324 tokens

kirby-project-tour

Maps a Kirby project using Kirby MCP tools/resources, including roots, templates, snippets, controllers, models, blueprints, plugins, runtime status, and key config. Use when a user wants a project overview, file locations, or a quick orientation before making changes.

bnomei/kirby-mcp · 58 tokens

agentic-qa-core

Foundation skill that hosts shared references cited by other workflow skills (briefing template, dispatch patterns, orchestration doctrine, skill composition strategy). Loaded on demand by shift-left-testing, sprint-testing, test-documentation, test-automation, regression-testing, project-discovery, adapt-framework…

upex-galaxy/agentic-qa-boilerplate · 115 tokens

agentic-qa-onboard

Walks new users through this repo's QA flow — Playwright + KATA + Allure + Xray stack, Jira QA workflow (Backlog → Shift-Left QA → Estimation → Ready For Dev → Ready For QA → In Test → QA Approved → Ready For Release → Deployed to Production), /shift-left-testing for pre-sprint AC refinement on backlog Stories…

upex-galaxy/agentic-qa-boilerplate · 500 tokens