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 skills/echoomegaprime/echo-qcoder/qcoder-browser-researchernpx skills add echoomegaprime/echo-qcoder --skill qcoder-browser-researchergit clone --depth 1 https://github.com/echoomegaprime/echo-qcoderWrote 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/echoomegaprime/echo-qcoder/qcoder-browser-researcher)<a href="https://agentmods.dev/skills/echoomegaprime/echo-qcoder/qcoder-browser-researcher"><img src="https://agentmods.dev/badge/skills/echoomegaprime/echo-qcoder/qcoder-browser-researcher.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 | $0.00071 | $0.00414 |
| Opus 5 | $0.00036 | $0.00207 |
| Sonnet 5 | $0.00014 | $0.00083 |
| Haiku 4.5 | $0.00007 | $0.00041 |
Grade A, and why
qcoder-browser-researcher 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
QCoder Browser Researcher
Expected input
Identify the fact or workflow to verify, the allowed domain or ECHO-owned account, and the evidence required. Prefer source code, local documentation, or an SDK capability when the web adds no value.
Required sequence
- Open or reserve a dedicated ShadowGlass tab and bind the action to the exact domain.
- Prefer primary official sources. Record page identity, publication or revision time when present, and the direct URL supporting each moving claim.
- For UI work, collect accessibility structure and visible text before clicking. Re-observe after navigation because selectors and layouts drift.
- Use bounded recovery: wait for a named condition, retry transient navigation once, re-acquire page state, then choose a different authorized path rather than repeating blind clicks.
- Use opaque Vault-to-browser transfer for credentials. Never read protected fields, cookies, tokens, or secret-bearing network bodies.
- Corroborate consequential UI claims with two evidence types such as visible text plus network response, accessibility state plus screenshot, or UI result plus backend read.
- Close or release the dedicated tab when the workflow is complete and persist only redacted evidence.
Browser-use is retained as a permissive reference for state, recovery, and domain-allowlist patterns. ShadowGlass remains QCoder's governed browser runtime.
Stop conditions
Stop on domain drift, protected-field mode, target-account uncertainty, an irreversible or public action outside the requested workflow, or anti-automation controls requiring a live human gesture.
Output format
Report the URL, observed time, actions, evidence, result, remaining uncertainty, and whether any external state changed.
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 · 31 lines · 71 tokens per session scan A db5232e03e51
qcoder-browser-researcher is a skill published in the GitHub repository echoomegaprime/echo-qcoder (0 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 414 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 2026-08-31.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.