set-acceptance-criteria

set-acceptance-criteria is a skill for Claude Code, Codex from cckyros/goal-acceptance. It costs 37 tokens per session (584 once invoked), scanned A, original, MIT.

A tool for defining and locking the acceptance criteria for a coding task before implementation. Acceptance criteria are observable conditions that describe when the work is done.

In plain words
What is it for?
Use it to set required and optional completion conditions for feature work, bug fixes, and refactors, usually after planning.
Why use it?
It turns a broad request into fixed, testable requirements and prevents criteria from changing during the same task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to set required and optional completion conditions for feature work, bug fixes, and refactors, usually after planning.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cckyros/goal-acceptance/set-acceptance-criteria
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 cckyros/goal-acceptance --skill set-acceptance-criteria
Clone the repo
git clone --depth 1 https://github.com/cckyros/goal-acceptance

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 set-acceptance-criteria

README.md
[![agentmods](https://agentmods.dev/badge/skills/cckyros/goal-acceptance/set-acceptance-criteria/github.svg)](https://agentmods.dev/skills/cckyros/goal-acceptance/set-acceptance-criteria)
Your own site
<a href="https://agentmods.dev/skills/cckyros/goal-acceptance/set-acceptance-criteria"><img src="https://agentmods.dev/badge/skills/cckyros/goal-acceptance/set-acceptance-criteria/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 set-acceptance-criteria

Your own site · 80×15
<a href="https://agentmods.dev/skills/cckyros/goal-acceptance/set-acceptance-criteria"><img src="https://agentmods.dev/badge/skills/cckyros/goal-acceptance/set-acceptance-criteria.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 584 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 $0.00037 $0.00584
Opus 5 $0.00018 $0.00292
Sonnet 5 $0.00007 $0.00117
Haiku 4.5 $0.00004 $0.00058

Measured 11d ago against content hash 7b1636297036, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

set-acceptance-criteria 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 11d 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.

assets/skills/set-acceptance-criteria/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before implementing, lock the goal's acceptance criteria. Criteria must be observable, have a unique id, and declare whether they are required for completion. Once locked, they cannot be modified for the current goal.

💡 Fast-path: Use the quick_start_goal tool to lock criteria and optional task plans in a single tool call.

When to Plan First

For any multi-step task (implement, fix, refactor), do NOT write criteria directly. Instead, use the goal-planning skill to spawn a planning subagent that:

  1. Explores the codebase to understand what the task touches
  2. Drafts criteria with goal-backward coverage analysis
  3. Checks for overlaps and gaps
  4. Submits via set_acceptance_criteria

This prevents the main agent from writing vague, incomplete, or overlapping criteria under execution pressure.

Criterion Quality Rules

Each criterion MUST have:

  • id: kebab-case, unique (e.g. api-200, core-default-role-agent)
  • description: concrete and verifiable, not vague
    • BAD: description: "error handling works"
    • GOOD: description: "fetchUser returns 404 when user not found"
  • required: true if the goal cannot be achieved without it
  • method: one of command | file | url — NEVER text
    • command: specify the exact command (e.g. pnpm test)
    • file: specify the exact file path to check
    • url: specify the exact URL and expected response
  • task_ids: linked task IDs for progress tracking

Role

Default role=agent: passed criteria are marked self-claimed, requiring confirm_criterion by an independent reviewer before completion.

Use role=reviewer or role=dual ONLY when the user explicitly waives independent review.

Example

{
  "criteria": [
    {
      "id": "api-200",
      "description": "GET /health returns HTTP 200 with { status: \"ok\" }",
      "required": true,
      "method": "command",
      "task_ids": ["t1"]
    },
    {
      "id": "docs-updated",
      "description": "README.md contains the new /health endpoint in the API table",
      "required": false,
      "method": "file",
      "task_ids": ["t2"]
    }
  ]
}

Read the full file on GitHub · 72 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. 11d ago First seen · 72 lines · 37 tokens per session scan A 7b1636297036

Subscribe to this mod's changes

set-acceptance-criteria is a skill published in the GitHub repository cckyros/goal-acceptance (3 stars, last pushed 14d ago), licensed MIT. It adds 37 tokens to every session and 584 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 2026-08-31.

Related

Other skills, from other repositories

dsh-web-skin-developer

Build a new skin for the dsh-web skin collection (DSH Web GUI) and publish it into the Skin Center — the first-level settings section — scaffold with scripts/dsh-skin-new, author the v2 skin.json manifest plus skin.css token remap (pure asset directory, no package.json, no build step), validate with scripts/dsh-skin…

zhu1090093659/dsh-web · 120 tokens

manage-taskboard

Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…

shengsheng90/DSH-taskboard · 88 tokens

yao-ocr

OCR text recognition expert. ALWAYS invoke this skill when you need to extract text from images or PDFs — including invoices, receipts, ID cards, bank cards, business licenses, tables, handwritten documents, or any visual text content.

YaoApp/yao · 50 tokens

yao-workspace

Workspace file I/O expert. ALWAYS invoke this skill when you need to list workspaces, read or write files in a workspace on a remote node, or browse workspace directories. Use this for cross-node file operations — for local sandbox files, use standard filesystem tools instead.

YaoApp/yao · 59 tokens

figma-code-connect

Creates and maintains Figma Code Connect template files that map Figma components to code snippets. Use when the user mentions Code Connect, Figma component mapping, design-to-code translation, or asks to create/update .figma.ts or .figma.js files.

Devin-AXIS/iPolloWork · 57 tokens

agentdebug

Use AgentDebugX for trajectory diagnosis only when the user explicitly asks to use AgentDebug, AgentDebugX, or the agentdebug skill. Do not invoke for generic debugging, diagnosis, inspection, or trajectory-review requests.

AgentDebugX/AgentDebugX · 47 tokens