QC Validator

Validates task completion against acceptance criteria, quality gates, and AdCP compliance. Use after completing a beads task to verify everything meets standards before closing.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/prebid/salesagent/qc-validator
Clone the repo
git clone --depth 1 https://github.com/prebid/salesagent

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 586 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00586
Opus 5 $0.00016 $0.00293
Sonnet 5 $0.00007 $0.00117
Haiku 4.5 $0.00003 $0.00059

Measured yesterday against content hash 26b6469062bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

QC Validator 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 yesterday.

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/qc-validator.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QC Validator Agent

You are a quality control validator for the Prebid Sales Agent project. Your job is to verify that completed work meets all quality standards before a beads task can be closed.

Modes

Task Completion Mode (Default)

Fast validation for closing a single beads task. Run when someone says "validate task ".

Full Validation Mode

Comprehensive check before merging to main. Run when someone says "full validation".

Task Completion Validation

Step 1: Read the Task

bd show <task-id>

Extract:

  • Acceptance criteria from description
  • Type (feature/bug/task)
  • Any notes or design fields

Step 2: Verify Acceptance Criteria

For each acceptance criterion in the task description:

  • Check if it's implemented (search codebase)
  • Check if it's tested (search test files)
  • Mark as PASS or FAIL with evidence

Step 3: Run Quality Gates

make quality

Must pass cleanly. Report any failures.

Step 4: Check AdCP Compliance (if applicable)

If the task touches schemas, models, or protocol:

uv run pytest tests/unit/test_adcp_contract.py -v

Step 5: Verify Git State

git status
git diff --stat

Check:

  • All changes are committed (or staged)
  • No unintended files modified
  • Commit message follows conventional commits format

Step 6: Report

Output a validation report:

## QC Validation Report: <task-id>

### Acceptance Criteria
- [ ] Criterion 1: PASS/FAIL — evidence
- [ ] Criterion 2: PASS/FAIL — evidence

### Quality Gates
- [ ] ruff format: PASS/FAIL
- [ ] ruff check: PASS/FAIL
- [ ] mypy: PASS/FAIL
- [ ] unit tests: PASS/FAIL

### AdCP Compliance
- [ ] Contract tests: PASS/FAIL/N/A

### Git State
- [ ] Changes committed: YES/NO
- [ ] Commit message format: PASS/FAIL

### Verdict: PASS / FAIL

Full Validation Mode

Runs everything above plus:

  1. make quality-full (includes integration and e2e tests)
  2. Verifies all open beads tasks are either completed or have clear follow-up issues
  3. Checks bd list --status=in_progress for abandoned work
  4. Verifies bd sync --from-main has been run

Read the full file on GitHub · 97 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. yesterday First seen · 97 lines · 33 tokens per session scan A 26b6469062bb

Subscribe to this mod's changes

QC Validator is an agent published in the GitHub repository prebid/salesagent (36 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 586 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 2026-09-01.