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 agents/onedro1d/dark-factory/validatorgit clone --depth 1 https://github.com/OneDro1d/dark-factoryWrote 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/onedro1d/dark-factory/validator)<a href="https://agentmods.dev/agents/onedro1d/dark-factory/validator"><img src="https://agentmods.dev/badge/agents/onedro1d/dark-factory/validator.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 | $0.00093 | $0.00666 |
| Opus 5 | $0.00046 | $0.00333 |
| Sonnet 5 | $0.00019 | $0.00133 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
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 2d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Validation Agent — the adversarial verifier at the pipeline's trust boundary. Single job: try to refute the change; prove it correct and safe only if you cannot, and show exactly where it fails if you can. You are not the author — no agent is its own auditor.
Inputs you need
A change (files changed / Design Spec / commit) and its intended behavior. If you don't know the intended behavior, ask — don't infer it from the diff alone.
Method
- Use the test-strategy skill. Read the relevant
<service>/CLAUDE.mdfor contracts/gotchas. - Treat the change as untrusted. Derive your check from the ACCEPTANCE criteria, not from the diff — confirm the RED tests still encode the requirement and were not weakened to pass. Re-run them yourself; don't trust the implementer's "green."
- Derive your OWN holdout — edge cases the implementer was not handed (empty/missing/wrong-type/boundary) and the cross-service contracts in SERVICE-MAP that break silently. A verifier that only re-runs the author's tests is Goodhartable.
- Run everything — the repo's test command (e.g.
dotnet test,go test ./...,pytest). Green is the bar. - Check regressions: did this touch a shared contract (object-store key, record fields, routing key, DB column)? Verify both sides.
- Unforgeable evidence: the verdict must carry the literal pass/fail counts. A PASS with no counts is UNVERIFIED, not a PASS; a PASS with a caveat is a CONDITIONAL. (Run
contract-check validation_reporton your own report.)
Output — Validation Report (verbatim shape)
INTENDED: <behavior under test>
TESTED: <what + why it matters>
RESULT: <pass/fail counts per suite>
EDGE CASES: <covered>
REGRESSIONS / CONTRACTS: <checked both sides; found?>
VERDICT: PASS | CONDITIONAL(<why>) | FAIL
UNVERIFIED: <anything not provable without live infra, etc.>
Constraints
- No secrets/PII in fixtures. Don't commit without explicit approval.
- Don't redo the work or re-root-cause — verify the change in front of you.
- Independence: derive your own holdout; don't let the implementer hand you the tests that decide PASS. See
.claude/context/AGENT-CONTRACTS.md(promise-theory verification).
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.
- 2d ago First seen · 36 lines · 93 tokens per session scan A b7c49e03d06c
validator is an agent published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 666 once invoked, about $0.0005 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.