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.
npx agentmods add skills/zeusyue/acceptance-driven-development-skill/acceptance-driven-developmentnpx skills add ZeusYue/acceptance-driven-development-skill --skill acceptance-driven-developmentgit clone --depth 1 https://github.com/ZeusYue/acceptance-driven-development-skillWrote 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.
[](https://agentmods.dev/skills/zeusyue/acceptance-driven-development-skill/acceptance-driven-development)<a href="https://agentmods.dev/skills/zeusyue/acceptance-driven-development-skill/acceptance-driven-development"><img src="https://agentmods.dev/badge/skills/zeusyue/acceptance-driven-development-skill/acceptance-driven-development.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00065 | $0.04958 |
| Opus 5 | $0.00032 | $0.02479 |
| Sonnet 5 | $0.00013 | $0.00992 |
| Haiku 4.5 | $0.00006 | $0.00496 |
Grade A, and why
acceptance-driven-development 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acceptance-Driven Development
Execute code changes against explicit acceptance criteria, then loop until every criterion has a settled outcome.
Completion layers: Agent implementation work is done only when no [ ] or [~] remain. The project is complete only when every AC is [x], [>], or [-] — no [ ], [~], or [!].
🚨 FIRST RULE — Check Before You Code
- Approved
[ ]/[~]backlog → Phase 3.5A → Mode A. - New feature or behavior change → Phase 3.5B → propose AC delta + approach → explicit approval → persist AC → Phase 4.
- Bug restoring intended behavior → Phase 3.5B impact analysis → fast lane; if no relevant AC exists, propose and confirm one before Phase 4.
- Refactor, build/config change, or pure cosmetic change → Phase 3.5B impact analysis → fast lane; untracked work also needs a confirmed tracking AC before Phase 4.
Describing a desired change is not approval of an approach. A fast-lane bug fix skips approach discussion, not impact analysis, review, or verification.
Announce: Phase 0, Gate 1, Gate 2, Phase 3.5A or 3.5B, Phase 4 Mode A or B, Phase 4.8, Phase 5, and Phase 6 when each begins.
Read references/guardrails-and-examples.md only when rationale, rationalization handling, scenarios, extended red flags, or the compact phase map is needed.
Capabilities and Scope
ADD is self-contained: AC parsing, impact analysis, review, verification, and completion checks must work even without companion skills.
| Optional capability | Use when available | Fallback |
|---|---|---|
| External planning tool | Mirror or assist ADD's approved-scope plan | Use the built-in plan asset/reference; never use tool status as acceptance status. |
| Review subagent | Mode A independent review | Explicit self-review against all six checks. |
project-experience |
Reuse cross-project lessons | Read $DOC_HUB/_exp_memory.md directly when present. |
What ships with it
12 files 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.
- assets/ac-document-tables.css 1.4 KB
- assets/ac-template-zh.md 5.0 KB
- assets/ac-template.md 5.5 KB
- assets/implementation-plan-template.md 2.6 KB
- assets/project-doc-template.md 8.6 KB
- assets/project-index.md 1.0 KB
- references/ac-contract-and-plan-boundary.md 6.5 KB
- references/change-design-guide.md 3.0 KB
- references/design-exploration-and-handoff.md 6.8 KB
- references/framework-review-checklist.md 2.1 KB
- references/guardrails-and-examples.md 6.0 KB
- references/implementation-planning-and-execution.md 13 KB
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.
- 3d ago First seen · 247 lines · 65 tokens per session scan A ebe5fe9dc6db
acceptance-driven-development is a skill published in the GitHub repository ZeusYue/acceptance-driven-development-skill (6 stars, last pushed 22d ago), licensed MIT. It adds 65 tokens to every session and 4,958 once invoked, about $0.0003 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.
Other skills, from other repositories
software-test-creation
Write failing tests for a TDD slice based on acceptance criteria and codebase conventions. Use when the "red" phase of red-green-refactor requires tests that define expected behavior before implementation exists. Discovers codebase test conventions first, writes test files that compile or parse but fail because the…
trellis-plan-review
Independent review of Trellis task planning artifacts. Treats the selected task and its recursive current or archived children as one review scope, verifies repository claims and path:line citations against code, traces every acceptance-criterion clause to a requirement and design mechanism, rechecks arithmetic and…
software-design-creation
Create software design specifications for new features or standalone software. Use when the user needs help turning a brief idea into a concrete design spec by eliciting missing requirements, clarifying scope, defining users and constraints, outlining architecture and interfaces, identifying risks and assumptions, and…
requirements-elicitation
Turns vague intent into testable requirements.
dev-cookbook
Requirement-aligned development workflow. TRIGGER: whenever the user asks to build a feature, make a change, optimize/improve something, or fix a bug — especially when the requirement is vague or lacks scope/acceptance criteria. Before starting, the agent MUST detect the user's role (PM/Developer/Both), persisted…
spec-index
Capture and retrieve durable project memory for spec-driven engineering, including decisions, constraints, setup steps, root causes, fixes, patterns, and reusable snippets through lightweight local indexing and keyword retrieval. Use this whenever the user wants to save knowledge for later, look up prior solutions…