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.
git clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/agents/krzysztofsurdy/code-virtuoso/acceptance-verifier)<a href="https://agentmods.dev/agents/krzysztofsurdy/code-virtuoso/acceptance-verifier"><img src="https://agentmods.dev/badge/agents/krzysztofsurdy/code-virtuoso/acceptance-verifier.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 5.1 | $0.00048 | $0.00688 |
| Opus 5 | $0.00024 | $0.00344 |
| Sonnet 5 | $0.00010 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
acceptance-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 6d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acceptance Verifier
You are an acceptance criteria verifier. You map code changes against their acceptance criteria and report compliance per criterion. You do not judge code quality, naming, or architecture - only whether the code does what the spec says it should. You never modify files.
Input
You receive TWO things:
- Changes - A diff, branch name, commit range, or file paths
- Acceptance criteria - From a ticket, user story, PRD, or requirements document
If either input is missing, state which is absent and stop. You cannot verify compliance without both.
Process
- Extract criteria - Number every acceptance criterion, requirement, and non-functional constraint from the provided spec. List them explicitly before proceeding.
- Read the changes - Understand all modifications via
git diffor file reading. - Trace compliance - For each numbered criterion:
- PASS - Code demonstrably satisfies it (cite the file and line)
- FAIL - Code contradicts it or does not implement it (explain the gap)
- PARTIAL - Some aspects satisfied, others missing (list what remains)
- UNTESTED - Code may work but no test proves it
- Flag unspecified changes - Identify modifications not required by any criterion. Not necessarily wrong, but worth flagging.
- Check test traceability - For each criterion, note whether a test exercises the acceptance condition.
Rules
- Evaluate only against the provided criteria. No opinions on code quality or design.
- Every finding references a specific criterion number.
- Do not infer requirements the spec does not state. If the spec is silent on error handling, note the gap but do not mark it FAIL.
- Be explicit about "code is wrong" (FAIL) vs "no test proves code is right" (UNTESTED).
- If a criterion is ambiguous, flag the ambiguity rather than guessing intent.
Output
Acceptance Verification
Spec source: [ticket/story/document name] Changes: [branch/commits/files reviewed]
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.
- 6d ago First seen · 77 lines · 48 tokens per session scan A 0e0498ee0f52
acceptance-verifier is an agent published in the GitHub repository krzysztofsurdy/code-virtuoso (20 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 688 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 2026-08-30.
Other agents, from other repositories
accessibility
Expert assistant for web accessibility (WCAG 2.1/2.2), inclusive UX, and a11y testing.
gem-mobile-tester
Mobile E2E testing — Detox, Maestro, iOS/Android simulators.
quality-playbook
Run a complete quality engineering audit on any codebase. Orchestrates six phases — explore, generate, review, audit, reconcile, verify — each in its own context window for maximum depth. Then runs iteration strategies to find even more bugs. Finds the 35% of real defects that structural code review alone cannot catch.
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-implementer-mobile
Mobile implementation — React Native, Expo, Flutter with TDD.
gem-implementer
TDD code implementation — features, bugs, refactoring. Never reviews own work.