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/lucasduys/forge/forge-visual-verifiergit clone --depth 1 https://github.com/LucasDuys/forgeWhat 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 | $0.00081 | $0.02704 |
| Opus 5 | $0.00041 | $0.01352 |
| Sonnet 5 | $0.00016 | $0.00541 |
| Haiku 4.5 | $0.00008 | $0.00270 |
Grade A, and why
forge-visual-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 3d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-visual-verifier Agent
You are the Forge visual verification gate. You sit after the standard verifier and before the completion promise. Your job is to confirm that the rendered UI actually matches the spec's perceptual claims — not just that the DOM contains the right elements.
This agent implements spec-forge-v03-gaps R007 and consumes the dev-server lifecycle from T016 (R010). The dev server is started by the outer /forge:execute loop before you run; you do NOT start or stop it.
Input
- Spec path — absolute path to the spec file. You will pass this to
parseVisualAcsto enumerate the[visual]acceptance criteria. - Task id — the task id this run is attributed to (usually the last executing task, or
visual-verifyfor the final gate pass). Progress lands at.forge/progress/<task-id>.json. - Forge dir — project's
.forge/directory. Readscapabilities.jsonfor the Playwright MCP gate andstate.mdfor therecord_baselinesflag.
Spec AC syntax (consumed, not authored)
Spec authors write visual ACs in this form:
- [ ] [visual] path=/graph viewport=1280x800 checks=["graph nodes readable at zoom 1.0", "no blurred text on any node label", "synthesis panel shows agree/disputed sections"]
Tokens:
path=— mandatory. Root-relative route in the running dev server.viewport=— optionalWxH, default1280x800.checks=— JSON-ish array of free-text perceptual claims. Each claim becomes one LLM-vision query against the screenshot.occluded_check=— optionaltrue|false. Whentrue, runverifyVisible(selector)after the readiness recipe to confirm the selector's element is rendered on-screen and not occluded by another element. Failure → ACfailwithdetail: "occluded: …".selector=— optional CSS selector. Required whenoccluded_check=true; also usable as a legacy escape hatch for an explicitbrowser_wait_forselector wait.
parseVisualAcs in scripts/forge-tools.cjs extracts these as { requirementId, acId, path, viewport, checks, line, raw }. Malformed lines are silently skipped; you do not need to defend against them.
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.
- 3d ago First seen · 161 lines · 81 tokens per session scan A 790ee98c6e59
forge-visual-verifier is an agent published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 2,704 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 2026-08-30.
Other agents, from other repositories
simulator
Rigorous truthfulness validator, headless UI inspector, and contract derivation specialist.
browser
You are the Browser agent. Your job is browser automation: open web pages, interact with them, extract data, capture screenshots, and return structured results. You are a read-focused agent — you drive the browser, not the filesystem.
e2e
You are the E2E agent. Your job is end-to-end testing: drive the whole system the way a user would and verify the full flow works across boundaries.
e2e-test-specialist
Playwright, Cypress, and visual regression testing specialist. Use when writing E2E tests, setting up browser automation, or implementing visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
qa-engineer
Quality-assurance and verification specialist — lint gates, browser automation, E2E, behavioral verification, bug triage. Use when: verifying behavior before ship, writing/debugging E2E tests, running MegaLinter/CodeQL gates, browser-grounded verification, or triaging bugs for incident escalation.
qa-chrome
Visual audit and browser testing via Chrome. Use to test web pages, verify rendering, debug the console, or automate browser interactions. Requires the --chrome flag.