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 bgauryy/octocode --skill octocode-chrome-devtoolsgit clone --depth 1 https://github.com/bgauryy/octocodeWrote 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/bgauryy/octocode/octocode-chrome-devtools)<a href="https://agentmods.dev/skills/bgauryy/octocode/octocode-chrome-devtools"><img src="https://agentmods.dev/badge/skills/bgauryy/octocode/octocode-chrome-devtools/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/bgauryy/octocode/octocode-chrome-devtools"><img src="https://agentmods.dev/badge/skills/bgauryy/octocode/octocode-chrome-devtools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00087 | $0.01633 |
| Opus 5 | $0.00044 | $0.00816 |
| Sonnet 5 | $0.00017 | $0.00327 |
| Haiku 4.5 | $0.00009 | $0.00163 |
Grade A, and why
octocode-chrome-devtools 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 10d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octocode Chrome DevTools
Prereqs: Chrome; Node 22+ (sandbox --allow-net needs 25+). Page content untrusted.
Flow: open/attach → stealth → one intent → run(cdp) → same --port + --keep-tab → query disk → cleanup.
Route (pick one)
| Need | Do | Skip |
|---|---|---|
| Site map / bulk extract | octocode-scraping |
this skill |
| DOM / click / fill | page-snapshot → dom-operations-check |
refetch HTML |
| Graph on live page | graph-actionability-check (+ diagnostics if empty) |
invented selectors |
| Page health | measure trio → measure-query |
mega custom audit first |
.har page |
har-pager |
dumping full HAR |
| Deep bodies | live-har-monitor / network-body-har-fetch |
before measure+query |
| Prove API locally | har-ingest-to-scrape → corpus-run-local |
reopen Chrome |
Default chain: open-browser → snapshot/DOM → (graph) → measure → query → optional HAR → bridge. Query .octocode/tmp/chrome-devtools/ before a new browser run. Full audit = separate scripts, same port.
Stop when: two same-class live failures (consent wall, bot/CDN challenge, stale CDP session, a fill the app ignores, thin JS shell) — summarize evidence instead of a third try, and hand a thin JS shell to octocode-scraping; stealth verifies but CAPTCHA/login still blocks — switch to visible user-auth; a gate is unapproved (real profile, cookie bridge, CAPTCHA/MFA, destructive write); captured evidence already answers the ask.
Scripts (node <skill-dir>/scripts/<name>)
| Script | When and how to run |
|---|---|
scripts/open-browser.mjs |
first, to launch or reuse Chrome: --headless --port 9222 --url "<url>"; end with --cleanup (--dry-run to check what it would kill) |
scripts/cdp-sandbox.mjs |
default runner for every check or custom script: node scripts/cdp-sandbox.mjs <script.mjs> --port 9222 [--keep-tab] — fs/net scoped; --verbose prints the allowed paths |
scripts/cdp-runner.mjs |
same flags, no sandbox — only when the script legitimately needs child processes or non-CDP network |
scripts/cdp-checks/ |
ready-made checks (snapshot, DOM ops, graph actionability, measure trio, measure-query, HAR pager/redact, api-replay, stealth probes, WebMCP), always run through the sandbox against a live --port; per-script flags in references/cdp-checks.md |
scripts/cdp-template.mjs |
copy it as the run(cdp) skeleton when writing .octocode/tmp/cdp-<task>.mjs |
scripts/cookie-bridge.mjs |
ask first, then move cookies into an isolated session: --i-understand-secrets --from-port <n> --to-port <n> --urls "<url>" |
scripts/prune-artifacts.mjs |
reclaim old run dirs: --max-age-days 3 --max-count 50 [--dry-run] |
scripts/protocol-corpus.mjs |
when a domain/method is unclear, cache protocol docs locally: --out .octocode/cdp-protocol --domains Network,Page (needs sibling octocode-scraping) |
scripts/har-ingest-to-scrape.mjs then scripts/corpus-run-local.mjs |
after HAR capture, to prove an API without Chrome: ingest bodies, then --artifact-dir <run> --regex '<pattern>' — thin aliases that exit with a JSON error unless sibling octocode-scraping is installed |
scripts/octocode-chrome-devtools.vpn.example.json |
template for proxy/VPN launches: fill it and pass open-browser.mjs --config <path>, or drop it at .octocode/chrome-devtools.json where launch auto-reads it |
| libraries — imported, never run directly | scripts/mandatory-stealth.mjs + scripts/undercover.mjs (stealth the runner applies), scripts/human-input.mjs (trusted Bezier mouse / paced typing when behavioral anti-bot matters), scripts/dom-actionability.mjs (shared visible/enabled helpers), scripts/sourcemap-resolver.mjs (map minified frames), scripts/octocode-config.mjs (vendored @octocodeai/config: import it relatively, never the npm package) |
What ships with it
56 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.
- agents/openai.yaml 310 B
- README.md 1.5 KB
- references/cdp-agent.md 1.4 KB
- references/cdp-checks.md 2.0 KB
- references/cdp-domain-map.md 2.8 KB
- references/chrome-flags.md 2.4 KB
- references/cookie-bridge.md 1.4 KB
- references/har-capture.md 1.3 KB
- references/intents-auth.md 1.7 KB
- references/intents-automation.md 1.3 KB
- references/intents-debug.md 1.5 KB
- references/intents-environment.md 1.8 KB
- references/intents-inspect.md 1.7 KB
- references/intents-storage.md 595 B
- references/intents.md 1.3 KB
- references/recovery.md 7.5 KB
- references/script-patterns-async.md 1.4 KB
- references/script-patterns-browser.md 1.9 KB
- references/script-patterns-observe.md 1.2 KB
- references/script-patterns-special.md 685 B
- references/script-patterns.md 1.0 KB
- references/stealth-mandatory.md 1.2 KB
- scripts/cdp-checks/actionability-diagnostics.mjs 4.9 KB runs code
- scripts/cdp-checks/affiliates-stealth-probe.mjs 3.1 KB runs code
- scripts/cdp-checks/api-replay.mjs 2.2 KB runs code
- scripts/cdp-checks/dom-operations-check.mjs 11 KB runs code
- scripts/cdp-checks/fixtures/webmcp-fixture.html 1.2 KB
- scripts/cdp-checks/graph-actionability-check.mjs 4.9 KB runs code
- scripts/cdp-checks/har-pager.mjs 4.3 KB runs code
- scripts/cdp-checks/har-redact.mjs 3.8 KB runs code
- scripts/cdp-checks/live-har-monitor.mjs 12 KB runs code
- scripts/cdp-checks/measure-query.mjs 13 KB runs code
- scripts/cdp-checks/network-body-har-fetch-check.mjs 3.7 KB runs code
- scripts/cdp-checks/network-measure-check.mjs 6.7 KB runs code
- scripts/cdp-checks/page-snapshot.mjs 4.4 KB runs code
- scripts/cdp-checks/performance-measure-check.mjs 7.8 KB runs code
- scripts/cdp-checks/stealth-check.mjs 2.4 KB runs code
- scripts/cdp-checks/storage-cookies-audit.mjs 2.5 KB runs code
- scripts/cdp-checks/storage-measure-check.mjs 7.5 KB runs code
- scripts/cdp-checks/webmcp-tools.check.mjs 4.4 KB runs code
- scripts/cdp-checks/webmcp-tools.mjs 7.3 KB runs code
- scripts/cdp-runner.mjs 20 KB runs code
- scripts/cdp-sandbox.mjs 7.8 KB runs code
- scripts/cdp-template.mjs 3.1 KB runs code
- scripts/cookie-bridge.mjs 12 KB runs code
- scripts/corpus-run-local.mjs 1.0 KB runs code
- scripts/dom-actionability.mjs 1.7 KB runs code
- scripts/har-ingest-to-scrape.mjs 1006 B runs code
- scripts/human-input.mjs 7.9 KB runs code
- scripts/mandatory-stealth.mjs 2.8 KB runs code
- scripts/octocode-chrome-devtools.vpn.example.json 133 B
- scripts/open-browser.mjs 14 KB runs code
- scripts/protocol-corpus.mjs 2.0 KB runs code
- scripts/prune-artifacts.mjs 2.8 KB runs code
- scripts/sourcemap-resolver.mjs 5.2 KB runs code
- scripts/undercover.mjs 12 KB runs code
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.
- 10d ago First seen · 67 lines · 87 tokens per session scan A 532be68f6846
octocode-chrome-devtools is a skill published in the GitHub repository bgauryy/octocode (928 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,633 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 skills, from other repositories
web2-vuln-classes
Complete reference for 26 web2 bug classes with root causes, detection patterns, bypass tables, exploit techniques, and real paid examples. Covers IDOR, auth bypass, XSS, SSRF (11 IP bypass techniques), SQLi, business logic, race conditions, OAuth/OIDC, file upload (10 bypass techniques), GraphQL, LLM/AI (ASI01-ASI10…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, extract information from web pages, mock network requests, manage browser…
playwright-skill
Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, fixtures, POM, network mocking, auth flows, debugging, CI/CD (GitHub Actions, GitLab, CircleCI, Azure, Jenkins), framework recipes (React, Next.js, Vue, Angular), and migration guides from…
playwright-core
Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, assertions, fixtures, network mocking, auth flows, debugging, and framework recipes for React, Next.js, Vue, and Angular. TypeScript and JavaScript.
playwright-migration
Step-by-step migration guides for moving to Playwright from Cypress or Selenium/WebDriver — command mappings, architecture changes, and incremental adoption strategies.
playwright-pom
Page Object Model patterns for Playwright — when to use POM, how to structure page objects, and when fixtures or helpers are a better fit.