ac-verifier

ac-verifier is an agent for Claude Code from HoangNguyen0403/agent-skills-standard. It costs 35 tokens per session (350 once invoked), scanned A, original, MIT.

A review assistant that checks numbered acceptance criteria against code changes, tests, and other implementation evidence. Acceptance criteria are the conditions a feature must meet.

In plain words
What is it for?
Use it to verify each criterion, cite supporting evidence, identify scope creep, and find requirements that have no implementation proof.
Why use it?
It makes it easier to see which requirements are complete, incomplete, or outside the agreed scope.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

Good fit Use it to verify each criterion, cite supporting evidence, identify scope creep, and find requirements that have no implementation proof.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hoangnguyen0403/agent-skills-standard/ac-verifier
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.

Clone the repo
git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard

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 ac-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/hoangnguyen0403/agent-skills-standard/ac-verifier/github.svg)](https://agentmods.dev/agents/hoangnguyen0403/agent-skills-standard/ac-verifier)
Your own site
<a href="https://agentmods.dev/agents/hoangnguyen0403/agent-skills-standard/ac-verifier"><img src="https://agentmods.dev/badge/agents/hoangnguyen0403/agent-skills-standard/ac-verifier/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 ac-verifier

Your own site · 80×15
<a href="https://agentmods.dev/agents/hoangnguyen0403/agent-skills-standard/ac-verifier"><img src="https://agentmods.dev/badge/agents/hoangnguyen0403/agent-skills-standard/ac-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 350 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 $0.00035 $0.00350
Opus 5 $0.00017 $0.00175
Sonnet 5 $0.00007 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 9d ago against content hash 1ee7af1b0b1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ac-verifier 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 9d 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.

.claude/agents/ac-verifier.md · 48 lines

What it actually says

Specialist: AC Verifier

Priority: P1 (HIGH)

Role

Verify each acceptance criterion against diff evidence, existing implementation, tests, and non-goals.

Budget

  • First pass: diff or supplied evidence only.
  • File cap: <= 1 file per unclear AC, <= 5 files total.
  • Use Jira/GitHub/GitLab/ADO/Zephyr/code graph MCPs only when configured.
  • No sub-agents.
  • If no AC list and no diff/evidence exist, return BLOCKED instead of guessing scope.

Steps

  1. Number ACs exactly as provided.
  2. Classify each AC: Fully Met, Partially Met, Not Met, or Pre-existing.
  3. Cite evidence: changed file, existing file, test, Zephyr TC, or walkthrough proof.
  4. Flag scope creep: changed behavior not mapped to any AC.
  5. If MCP unavailable, ask for exported ticket/PR text or use local artifacts.

Output

### AC Verification
| # | Acceptance Criteria | Status | Evidence |
| --- | --- | --- | --- |
| [AC] | [text] | [status] | [evidence] |

#### Scope Creep
- [item or None]

#### Missing ACs
- [item or None]

Anti-Patterns

  • No architecture/security/test commentary unless it directly affects AC status.
  • No ticket-scope violation unless scope tags/non-goals were checked.
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. 9d ago First seen · 48 lines · 35 tokens per session scan A 1ee7af1b0b1c

Subscribe to this mod's changes

ac-verifier is an agent published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 350 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.

Related

Other agents, from other repositories

doc-writer

A documentation-focused coding agent for technical writing, API documentation, user guides, READMEs, changelogs, and similar documents.

AsiaOstrich/universal-dev-standards · 63 tokens

reviewer

A code-review specialist for checking changes for quality, security issues, and common engineering practices.

AsiaOstrich/universal-dev-standards · 67 tokens

spec-analyst

A specialist for turning requirements into clear specifications, including extracting specifications from existing code.

AsiaOstrich/universal-dev-standards · 58 tokens

uds-architecture-reviewer

Use proactively to review a large or structural change, decide a module boundary, or diagnose a failure whose cause is not yet hypothesised. Use when only the goal and the constraints are known and the path has to be found rather than applied. Read-only — it reports findings and does not edit files.

AsiaOstrich/universal-dev-standards · 67 tokens

uds-deep-investigator

Use for work larger than a single sitting that must run unattended — a root-cause investigation with no hypothesis yet, an outage post-mortem across several systems, or an architecture decision whose options are not yet enumerated. Use when the agent will have to investigate, verify its own work, and keep the thread…

AsiaOstrich/universal-dev-standards · 88 tokens

uds-feature-implementer

Use to implement a feature whose goal and integration points are already defined, refactor a module toward a stated target structure, or write integration tests for a specified subsystem. Use when most steps are settled and only a bounded set of local choices remains. Do NOT use when the target structure itself is…

AsiaOstrich/universal-dev-standards · 74 tokens