define-acceptance

define-acceptance is a skill for Claude Code from tomzx/agents. It costs 36 tokens per session (690 once invoked), scanned A, original, MIT.

A requirements workflow that turns product requirements and desired results into testable acceptance criteria. Acceptance criteria are conditions that must be true for work to count as complete.

In plain words
What is it for?
Use it to write Given/When/Then or measurable criteria, connect them to success and safety metrics, and mark what is included or excluded from the initiative.
Why use it?
It creates a clear handoff between product and engineering by defining observable results without prescribing how the software must be built.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to write Given/When/Then or measurable criteria, connect them to success and safety metrics, and mark what is included or excluded from the initiative.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/define-acceptance
View source ↗ tomzx/agents
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 tomzx/agents --skill define-acceptance
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code.

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 define-acceptance

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/define-acceptance"><img src="https://agentmods.dev/badge/skills/tomzx/agents/define-acceptance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 690 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 $0.00036 $0.00690
Opus 5 $0.00018 $0.00345
Sonnet 5 $0.00007 $0.00138
Haiku 4.5 $0.00004 $0.00069

Measured 5d ago against content hash 649ef764f8bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

define-acceptance 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 5d 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.

skills/pdlc/skills/define-acceptance/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Define Acceptance

This skill produces the acceptance contract: the testable, outcome-linked criteria that form the handoff from PDLC to SDLC. It is the seam. SDLC's create-requirements consumes this contract directly.

The contract captures what must be true for the initiative to be accepted (linked to SM-N success metrics and FR-N requirements), expressed so an engineer and a PM can both verify it. It deliberately excludes implementation.

Prerequisites

  • Apply the shared PDLC conventions in skills/pdlc/references/shared.md.
  • prd.md with functional requirements and success criteria.

Steps

  1. Translate each functional requirement (FR-N) into one or more acceptance criteria in Given/When/Then or measurable form. Each criterion must be verifiable by behavior or measurement, not by code inspection alone.
  2. Bind each success metric (SM-N) to an acceptance criterion: "accepted only if SM-N reaches target within the window."
  3. Bind guardrails: list every GM-N that must hold post-launch as a hard acceptance line ("must not regress below floor").
  4. Define the acceptance boundary: what is in scope (must pass) vs. explicitly out of scope (the non-goals from the PRD).
  5. Record the decomposition into SDLC features: one initiative commonly spawns one or more FEAT-N. List spawns_features in the initiative frontmatter.
  6. Note which criteria need runtime/analytics proof (feed spec-analytics) vs. functional proof (feed SDLC tests).
  7. Write acceptance-contract.md to the initiative directory.

Output Format

Use the template at skills/pdlc/templates/initiatives/acceptance-contract.md. Each criterion carries an AC-N id and links to its FR-N / SM-N / GM-N.

Outcome

If $OUTCOME_YAML is set, emit verdict: ready-for-sdlc.

The Handoff

After the Define gate proceed:

  • Point the user to /sdlc requirements with this contract as input. PDLC does not run SDLC skills itself.
  • SDLC produces requirements.mdspecification.md → plan → code → PR, and the acceptance criteria become SDLC test cases (TC-N).
  • PDLC resumes at plan-launch once the change is shipped.

Read the full file on GitHub · 54 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. 5d ago First seen · 54 lines · 36 tokens per session scan A 649ef764f8bc

Subscribe to this mod's changes

define-acceptance is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 690 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 2026-09-03.