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 skills add manishiitg/coding-agent-loop --skill browser-performance-validationgit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/skills/manishiitg/coding-agent-loop/browser-performance-validation)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/browser-performance-validation"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/browser-performance-validation/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/skills/manishiitg/coding-agent-loop/browser-performance-validation"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/browser-performance-validation.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 | $0.00036 | $0.00673 |
| Opus 5.5 | $0.00014 | $0.00269 |
| Sonnet 5.5 | $0.00007 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
browser-performance-validation 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Performance Validation
Outcome
Create repeatable browser performance measurements for approved pages and journeys, compare them with customer budgets or baselines, and retain enough provenance and diagnostics to explain regressions.
When to use
Use after browser setup for performance budgets, trend tracking, or release checks. Treat results as environment-specific observations unless the customer provides a controlled benchmark environment.
Discovery and user direction
Inspect the current workflow, goals, metrics, configuration, capabilities, stores, reports, and triggers before proposing changes. Summarize reusable design and gaps, then ask focused questions for unresolved customer choices such as scope, success, approvals, thresholds, ownership, and budgets. Record the answers as customer direction. Installation alone does not approve workflow changes or execution. Default to one small-team workflow; split only for incompatible access or lifecycle boundaries.
Required inputs
Resolve target pages/journeys, tested build, browser/device/network profile, cold/warm-cache policy, sample count, metrics, budgets or baseline, acceptable variance, evidence retention, and pass/fail policy.
Plan and AgentWorks tools
Use scripted steps for controlled execution, metric collection, aggregation, comparison, and persistence. Use a message sequence to investigate supported regressions. Keep warmup and measured samples explicit; do not let an agent invent thresholds after seeing results.
Knowledge and persistence
Store raw samples, aggregates, budgets, environment/profile identity, and comparison results in durable DB tables. Store traces, video, console/network logs, and exported profiles in durable assets. Put reusable application performance facts in KB notes only after verification.
Validation and reporting
Require the configured number of valid samples and comparable provenance. The dashboard shows the customer's chosen aggregates, variance and budget status, filters for journey/browser/device/build/environment, and drill-down to samples, traces, evidence, missing metrics, invalid samples, and history. A partial measurement set cannot silently pass.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 53 lines · 36 tokens per session scan A 85cdd8d269dd
browser-performance-validation is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 36 tokens to every session and 673 once invoked, about $0.0001 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 2026-09-14.
Other skills, from other repositories
herdr-gpui-browser
Open a browser tab in Herdr GPUI to show the user a web page or an HTML file you wrote, next to the terminal you run in, and get back the notes the user pins on it. Use whenever the user asks to open, start, or show a browser tab, a page, a preview, or a mockup while you run inside Herdr (HERDRENV=1 is set in your…
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron apps — navigating, forms, clicks, screenshots, data extraction, testing web apps, UI checks, the dashboard Electron shell, or the user's own logged-in Chrome via the browser relay or Panerelay (SSO/2FA). Triggers: "open…
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
creating-actions
This skill should be used when the user asks to "create an action", "save this flow as an action", "make this replayable", "record a reusable action", "author a Maestro flow as an action", "add a login/setup action", or when a verified UI walk should be persisted under .rn-agent/actions/ so future sessions can replay…
record-browser-gif
Record browser or Web UI interaction demos as optimized GIFs using the available built-in browser, state-based frame capture, and deterministic encoding, then publish to a dedicated assets branch when the task includes attaching the GIF to a pull request. Use when asked to make, record, or generate a GIF that…