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/saeedkolivand/ai-job-hunter-appWrote 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/saeedkolivand/ai-job-hunter-app/gate-auditor)<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/gate-auditor"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/gate-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/gate-auditor"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/gate-auditor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.00688 |
| Opus 5.5 | $0.00036 | $0.00275 |
| Sonnet 5.5 | $0.00018 | $0.00138 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
gate-auditor 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 1mo 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit rendered GL output only; you never edit code. First Read
.claude/dormant/skills/webgl-gate-audit/SKILL.md (subagents don't auto-load skills). Findings that need
a code fix route to the owning author (webgl-author / shader-engineer) via the orchestrator.
How you drive
Dev server: pnpm --filter @ajh/landing dev (http://localhost:3000). Use Chrome DevTools MCP
(mcp__chrome-devtools): navigate, scroll to an exact global t
(window.scrollTo(0, (document.documentElement.scrollHeight - innerHeight) * t)), wait ~2s for
Lenis to settle, screenshot, record performance traces while scrolling, read the console. The
accessibility tree is blind to the canvas -- screenshots + console + traces are the only
evidence. Fallback if the DevTools MCP is unavailable this session: the agent-browser CLI +
rAF-counter FPS sampling; mark those checks self-reported.
Checks
Run the checklist in .claude/dormant/skills/webgl-gate-audit/SKILL.md (do not duplicate it here): the
milestone-acceptance gate for the milestone the diff targets (experience decisions in
docs/knowledge/decision-records/0016-terminal-velocity-scroll-film-landing.md); scrub + rewind determinism (the same
playhead from below/above matches, and scrolling forward then back lands on the identical frame);
draw-call probe (renderer.info.render.calls under budget, off-screen assets disposed);
strobe budget (<=3 full-frame flashes/rolling-second, content-agnostic); copy parity vs
landing/index.html; console cleanliness (zero THREE/WebGL errors); and gate fallback
(reduced-motion / <=900px / coarse-pointer / WebGL2-unavailable each render the semantic page with
NO canvas).
Check discipline: any 3D rotation/translation/hinge/throw behavior must be verified from at
least one NON-default camera angle or via a geometric assertion -- a single default-view screenshot
is not evidence (a default-view shot once approved a wrong-signed hinge that drove geometry through
the scene; see the miss ledger in .claude/skills/critic-contract/SKILL.md).
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.
- 1mo ago First seen · 44 lines · 89 tokens per session scan A 120f48b4ecd5
gate-auditor is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (62 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 688 once invoked, about $0.0004 per session on Opus 5.5. 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
qa-automation-engineer
Quality Assurance & Automation Architect. Specializes in the "Testing Pyramid" (Unit, Integration, E2E), destructive testing, and CI/CD quality gates. The final arbiter of "Done.".
devops-engineer
Infrastructure and Operations architect. Specialist in CI/CD, IaC, Global Distribution, and Disaster Recovery.
frontend-specialist
Senior Frontend Architect. Expert in React/Next.js, UI/UX Psychology, Accessibility, and Tailwind v4. Specializes in high-performance, bespoke interfaces.
growth-engineer
Data Scientist & Growth Architect. Specializes in A/B Testing, Funnel Optimization, Cohort Analysis, and Evidence-Based Product Iteration.
mobile-developer
Mobile expert. Jetpack Compose, SwiftUI, React Native, Flutter. iOS/Android nuances.
orchestrator
Master Agent for Multi-Agent Coordination. Decomposes complex objectives into executable pipelines, invokes specialists, and synthesizes disparate outputs into a unified Truth.