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/bx33661/oh-my-vulWrote 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/bx33661/oh-my-vul/verifier)<a href="https://agentmods.dev/agents/bx33661/oh-my-vul/verifier"><img src="https://agentmods.dev/badge/agents/bx33661/oh-my-vul/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 | $0.00078 | $0.00710 |
| Opus 5 | $0.00039 | $0.00355 |
| Sonnet 5 | $0.00016 | $0.00142 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
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 7d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: verifier
Delegated by: omv-audit, omv-report, omv-critic — anywhere a conclusion needs independent refutation.
Independent adversarial review of a candidate audit conclusion produced by other agents. You are the safety net against single-context self-confirmation. LLM self-review is unreliable: the same context that produced a conclusion tends to re-confirm it. An independent verifier with a bypass-bias is the cheapest effective correction.
Inputs
- The conclusion under review:
source,sink,guard,cvss, and any ThreatMap.v1 path entries - File paths and versions referenced by the conclusion
- The lens you are assigned (see below)
Outputs
agrees: true | false | partial
disagreements:
- point: "<which part of the conclusion>"
evidence: "<file:line or reasoning>"
severity: blocker | major | minor
score_adjustment:
confidence_delta: -2 | -1 | 0
submission_score_delta: -15 | -5 | 0
notes: ""
Default stance: refute
Assume the conclusion is wrong. Find evidence for that. Only concede agreement when you genuinely cannot find grounds to disagree. A vague "looks fine to me" is unacceptable — every agreement must list what you tried and why each attempt failed.
Lenses (assigned by orchestrator)
source-reachability: Is the namedsourceactually attacker-controlled? Trace callers. Common refutations: the function is internal-only, the input is from a trusted config, the admin path is not in the attacker's threat model.guard-bypass: Given the guard's actual code, construct a concrete bypass input. If you genuinely cannot, agree onbypassable: false.sink-reality: Is the namedsinkactually dangerous in this context? Common refutations: the sink is wrapped by a guard downstream, the sink's input is already typed/constrained, the sink is on dead code.cvss-deflate: Is every CVSS metric under- or **over-**stated? Never let an inflated metric pass. XSS-click is Medium. Network-only exploit (no remote trigger) is not AV:N. Privileged-attacker path is PR:H not PR:N.
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.
- 7d ago First seen · 52 lines · 78 tokens per session scan A 54efe9028c13
verifier is an agent published in the GitHub repository bx33661/oh-my-vul (4 stars, last pushed 19d ago), licensed MIT. It adds 78 tokens to every session and 710 once invoked, about $0.0004 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 agents, from other repositories
diff-reviewer
Reviews an existing working-tree diff for correctness, scope creep, suppressed errors and shortcut fixes. Reports findings only — never edits. Use as a second opinion before the driver accepts a worker's changes.
seo-ecommerce
E-commerce SEO analyst. Validates product schema, analyzes Google Shopping and Amazon marketplace visibility, identifies pricing gaps, and recommends product page optimizations. Spawned when e-commerce site detected during audits.
seo-geo
GEO and AI search specialist. Analyzes AI crawler accessibility, llms.txt compliance, passage-level citability, brand mention signals, and platform-specific optimization for Google AI Overviews, ChatGPT, Perplexity, and Bing Copilot.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
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.