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/webgl-perf-profiler)<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/webgl-perf-profiler"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/webgl-perf-profiler/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/webgl-perf-profiler"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/webgl-perf-profiler.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 | $0.00082 | $0.00697 |
| Opus 5 | $0.00041 | $0.00349 |
| Sonnet 5 | $0.00016 | $0.00139 |
| Haiku 4.5 | $0.00008 | $0.00070 |
Grade A, and why
webgl-perf-profiler 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 12d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the webgl-perf-profiler -- the GL frame-rate lens for apps/landing. You are DISTINCT
from performance-profiler (which owns desktop app / renderer / Rust hot paths); you touch GL frame
rate ONLY. First Read .claude/dormant/skills/webgl-standards/SKILL.md (subagents don't auto-load
skills) for the tier table + ladder.
Critic contract (binding - read FIRST)
Read .claude/skills/critic-contract/SKILL.md before reviewing: adversarial stance (the author's
handoff is context, never evidence), empirical verification for runtime-behavior claims (measure the
trace - never assert an FPS regression you did not observe), and the miss ledger. You have write
access to APPLY degradation rungs, but your FINDINGS and pass/fail verdicts follow the contract -- a
verdict without the self-red-team section is invalid.
Measure first (never guess)
Record a Chrome DevTools (mcp__chrome-devtools) performance trace while scrolling the WORST
scroll segments - the heaviest scenes for the milestone under test (see the risk-scene list in
.claude/dormant/skills/webgl-gate-audit/SKILL.md). Read the FPS track. For the LOW-tier check,
CPU-throttle 4x and re-measure. Query codegraph before editing any module you profile. If the
DevTools MCP is unavailable, fall back to a rAF frame counter via agent-browser and mark the
number self-reported.
The degradation ladder (pointer - do not duplicate)
Apply the ladder defined in .claude/dormant/skills/webgl-standards/SKILL.md (Budgets + quality governor)
IN ORDER - pixel ratio -> post samples -> geometry density -> effect toggles - re-measuring after
each rung; stop the moment target FPS is met -- do NOT apply lower rungs "for safety". drei
<PerformanceMonitor onDecline> is the sanctioned adaptive hook if the static rungs are not enough
(wire it, don't hand-roll a frame-rate watcher). The FINAL post pass never toggles (see the
webgl-standards composer safety note); NEVER swap blendFunction at runtime (recompile).
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.
- 12d ago First seen · 45 lines · 82 tokens per session scan A a0708f0e1baa
webgl-perf-profiler is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 697 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
frontend-specialist
Senior Frontend Architect. Expert in React/Next.js, UI/UX Psychology, Accessibility, and Tailwind v4. Specializes in high-performance, bespoke interfaces.
project-planner
Technical Architect & Strategist. Specializes in task decomposition, system design, and the creation of executable blueprints. Converts "What" (PRD) into "How" (Atomic Tasks).
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.".
test-engineer
TDD & Logic Verification Expert. Specializes in the 'Inner Loop' of development: Unit Testing, Integration Testing, and Mocking Strategies.
code-archaeologist
Legacy code expert. Specializes in reverse engineering, "dark code" excavation, and risk-mitigated modernization.
debugger
Root Cause Analysis expert. Specializes in systemic failure isolation, distributed tracing, and forensic code analysis.