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 Jonathangadeaharder/AgentBible --skill camoufoxgit clone --depth 1 https://github.com/Jonathangadeaharder/AgentBibleWrote 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/jonathangadeaharder/agentbible/camoufox)<a href="https://agentmods.dev/skills/jonathangadeaharder/agentbible/camoufox"><img src="https://agentmods.dev/badge/skills/jonathangadeaharder/agentbible/camoufox/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/jonathangadeaharder/agentbible/camoufox"><img src="https://agentmods.dev/badge/skills/jonathangadeaharder/agentbible/camoufox.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 | $0.00116 | $0.17399 |
| Opus 5.5 | $0.00046 | $0.06960 |
| Sonnet 5.5 | $0.00023 | $0.03480 |
| Haiku 4.5 | $0.00012 | $0.01740 |
Grade B, and why
camoufox scanned grade B with 2 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 2mo 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
27. **Tab creation timeout after server restart**: If the server was killed while a persistent profile had stale storage state, new tab creation can hang for 30s then return `500 tab create timed out`. **Fix**: delete th Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Direct REST API with custom userId** | `references/direct-rest-api-custom-userid.md` | When cookies are pre-injected for a specific userId, Hermes browser tools can't be used — drive the REST server directly via curl The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
54 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.
- references/actor-checker-automation.md 3.5 KB
- references/alibaba-baxia-captcha.md 5.0 KB
- references/amazon-cookie-injection.md 8.1 KB
- references/amazon-return-workflow.md 3.2 KB
- references/amazon-spa-declarative-limitation.md 5.9 KB
- references/angular-spa-form-automation.md 7.7 KB
- references/automation-patterns.md 22 KB
- references/ba-secure-2fa.md 8.2 KB
- references/browser-ctrl.md 10 KB
- references/camoufox-playwright-gotchas.md 6.4 KB
- references/camoufox-ubo-setup.md 1.8 KB
- references/captcha-bypass.md 19 KB
- references/captcha-trajectory-recorder.md 5.6 KB
- references/clerk-modal-automation.md 8.1 KB
- references/credential-rotation.md 10 KB
- references/direct-rest-api-custom-userid.md 4.7 KB
- references/dominos-ordering.md 12 KB
- references/engine-test-results.md 6.3 KB
- references/github-profile-pinning.md 11 KB
- references/headless-mode.md 2.6 KB
- references/hermes-browser-camofox-backend.md 6.1 KB
- references/huk24-e-scooter-insurance.md 6.0 KB
- references/lieferando-address-input.md 4.4 KB
- references/lieferando-checkout.md 57 KB
- references/lieferando-menu-scraping.md 6.4 KB
- references/lovable-source-extraction.md 7.8 KB
- references/perimeterx-surfshark-vpn.md 2.6 KB
- references/persistent-context-google-auth.md 2.9 KB
- references/playwright-firefox-bugfix.md 2.3 KB
- references/ryanair-angular-picker.md 11 KB
- references/ryanair-angular-spa.md 4.9 KB
- references/ryanair-spa-selectors.md 4.7 KB
- references/security-incident-response.md 7.6 KB
- references/signature-pad-automation.md 5.5 KB
- references/starlink-account-portal.md 2.7 KB
- references/stytch-auth.md 4.5 KB
- references/wop-webshop.md 11 KB
- scripts/actor_checker.py 11 KB runs code
- scripts/amazon_order_automation.py 6.6 KB runs code
- scripts/ba_login_camoufox.py 4.6 KB runs code
- scripts/browser_repl.py 11 KB runs code
- scripts/camoufox_cli.py 4.4 KB runs code
- scripts/camoufox_server.py 4.7 KB runs code
- scripts/camoufox-cookie-injection.py 4.5 KB runs code
- scripts/capsolver.py 4.2 KB runs code
- scripts/captcha_flow.py 2.3 KB runs code
- scripts/extract_firefox_cookies.py 5.0 KB runs code
- scripts/extract_menu.js 1.9 KB runs code
- scripts/hold_click.swift 1.9 KB
- scripts/inject_ba_cookies.py 2.7 KB runs code
- scripts/lieferando_extract_menu.js 1.3 KB runs code
- scripts/prevention.py 4.5 KB runs code
- scripts/record_mouse.swift 2.5 KB
- scripts/ryanair.py 11 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.
- 2mo ago First seen · 600 lines · 116 tokens per session scan B c4e44bbf2b7c
camoufox is a skill published in the GitHub repository Jonathangadeaharder/AgentBible (2 stars, last pushed 3mo ago), with no licence file. It adds 116 tokens to every session and 17,399 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
camoufox compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| camoufoxJonathangadeaharder/AgentBible | Skill | 2 | 3mo ago | none | B | 116 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | today | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 906 | yesterday | MIT | A | 40 | Claude Code |