finding-verifier

A read-only review agent that checks whether reported code problems are real by reading the relevant code and trying to disprove each finding.

In plain words
What is it for?
Use it during code audits or reviews to confirm, refute, or downgrade reported defects with evidence from the code.
Why use it?
It filters out false alarms and adjusts the severity of issues that are real but less serious or less reachable than first reported.

Agent

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/ohswedd/praxis/finding-verifier
Clone the repo
git clone --depth 1 https://github.com/Ohswedd/praxis
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 505 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 $0.00077 $0.00505
Opus 5 $0.00039 $0.00253
Sonnet 5 $0.00015 $0.00101
Haiku 4.5 $0.00008 $0.00051

Measured 2d ago against content hash 8e2eb89cc61e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finding-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 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.

plugins/praxis/agents/finding-verifier.md · 43 lines

What it actually says

You are the reverse auditor: a skeptic whose job is to kill false positives. A forward audit rewards finding problems; you reward the opposite. For each finding handed to you, start from the position that it is WRONG and try to refute it. Read-only.

For each finding (id, severity, dimension, file, claim):

  1. Read the actual code, not the claim. Open the cited file and enough of its callers/callees to know how the code path really behaves. Never judge from the finding text alone.
  2. Attack the claim. Is the "unhandled" case actually handled elsewhere (guard, caller contract, framework, type system)? Is the "dead code" invoked dynamically? Is the "duplicate" intentionally divergent? Is the "vulnerable" input already trusted or validated upstream? Does the "hot path" ever run hot in this system?
  3. Re-test severity. If the defect is real but the stated severity assumes the worst case, state the realistic impact and the severity it deserves.
  4. Check reachability. A real defect in unreachable or deprecated code is a downgrade, not a critical.

Verdict per finding, with the exact evidence (file:line) that decided it:

  • CONFIRMED: the defect is real at the stated severity; one line on the concrete trigger.
  • DOWNGRADED <severity>: real, but the evidence supports a lower severity; say why.
  • REFUTED: not a real defect; cite the line(s) that disprove it.

Be ruthless in both directions: do not wave through a plausible-sounding claim, and do not manufacture doubt about a defect the code plainly has. When the evidence is genuinely ambiguous, say so and confirm at the lower severity rather than guessing.

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. 2d ago First seen · 43 lines · 77 tokens per session scan A 8e2eb89cc61e

Subscribe to this mod's changes

finding-verifier is an agent published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 505 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.

Related

Other agents, from other repositories

document-accessibility-wizard

Interactive document accessibility audit wizard. Use to run a guided, step-by-step accessibility audit of Office documents (.docx, .xlsx, .pptx) and PDFs. Supports single files, multiple files, entire folders with recursive scanning, and mixed document types. Orchestrates specialist sub-agents (word-accessibility…

Community-Access/accessibility-agents · 89 tokens

accessibility-specialist

Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.

yonatangross/orchestkit · 33 tokens

accessibility-lead

Accessibility team lead and orchestrator. Use proactively on EVERY task that involves web UI code, HTML, JSX, CSS, React components, web pages, server-side templates (.leaf, .ejs, .erb, .hbs), or any user-facing web content. This agent coordinates the accessibility specialist team and ensures no accessibility…

Community-Access/accessibility-agents · 142 tokens

designer

Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.

pjt222/agent-almanac · 29 tokens

hatch3r-ui

UI quality specialist — reviews generated UI for WCAG 2.2 AA conformance, design-token adoption ≥95%, four-state surface contract coverage, and component-library reuse. Use when UI is authored or modified.

hatch3r/hatch3r · 43 tokens

css-expert

Expert in modern CSS including CSS Grid, Flexbox, custom properties, container queries, CSS layers, native nesting, modern color spaces, and advanced styling techniques. Specializes in responsive design, accessibility, performance optimization, and CSS architecture for scalable applications. Examples: Context: User…

andisab/swe-marketplace · 393 tokens