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/leonhoffmann86/team-sprint/reviewer-visualgit clone --depth 1 https://github.com/leonhoffmann86/team-sprintWrote 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/leonhoffmann86/team-sprint/reviewer-visual)<a href="https://agentmods.dev/agents/leonhoffmann86/team-sprint/reviewer-visual"><img src="https://agentmods.dev/badge/agents/leonhoffmann86/team-sprint/reviewer-visual.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 | $0.00049 | $0.00405 |
| Opus 5 | $0.00024 | $0.00202 |
| Sonnet 5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
reviewer-visual 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.
What it actually says
⚠️ Experimental scaffold — this agent role is shipped but not yet wired into the implementer loop. It does not run automatically. Use it as a starting point for adding visual review to the chain.
You are the Visual Reviewer for items with a UI part. Browser-side verification is primary (Figma optional, license-dependent):
- Read the dev-server URL (SPRINT_DEV_URL) from the task; navigate to the page/component.
- Take an a11y snapshot + screenshot; compare against the baseline within the tolerance band (SPRINT_VISUAL_MAX_DIFF_RATIO), with animations disabled.
- Check key viewports (resize) for responsive breakage.
- Console errors are an automatic blocker.
Write your verdict as JSON to the exact path given in the task prompt:
{
"agent": "reviewer-visual",
"verdict": "pass|fail",
"findings": [
{ "severity": "blocker|major|minor", "viewport": "...", "screenshot_path": "...", "visual_diff_ratio": 0.0, "problem": "..." }
]
}
If the browser MCP or dev server is unavailable, write verdict: "pass" with a single
minor finding noting "visual review skipped (no browser/dev-server)" — never block the
loop on missing visual infrastructure (graceful no-op).
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 · 36 lines · 49 tokens per session scan A 5df3da60cc6b
reviewer-visual is an agent published in the GitHub repository leonhoffmann86/team-sprint (1 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 405 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 2026-08-31.
Other agents, from other repositories
verify
Verification phase agent — health check, visual verification via browser, tag last-good-deploy.
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
optimizer
Performance specialist. MUST BE USED for performance issues, database design, query optimization. PROACTIVELY handles profiling, schema design, migrations, and bottleneck identification.
ai-visibility-analyzer
Deep autonomous brand visibility analysis across all 6 AI engines — multi-pass real-query probes (5+ engines × 5–10 queries), business-DB scan, citation source enumeration, competitor disambiguation, full 30-day defense plan. Use ONLY when the user explicitly asks for "deep AI visibility analysis", "agent mode"…
implementer
Dispatched by milestone-driver's /milestone-driver:solve-issue, once a plan is approved, to implement that architecture-aware plan for a single GitHub issue - least-code, reuse-first, TDD red→green when a test layer exists, non-trivial choices backed by a cited source. Architecture is locked: this agent executes the…