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 axiom-browser-automation/claude-skill --skill axiomgit clone --depth 1 https://github.com/axiom-browser-automation/claude-skillWrote 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/axiom-browser-automation/claude-skill/axiom)<a href="https://agentmods.dev/skills/axiom-browser-automation/claude-skill/axiom"><img src="https://agentmods.dev/badge/skills/axiom-browser-automation/claude-skill/axiom/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/axiom-browser-automation/claude-skill/axiom"><img src="https://agentmods.dev/badge/skills/axiom-browser-automation/claude-skill/axiom.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 | $0.00146 | $0.06742 |
| Opus 5 | $0.00073 | $0.03371 |
| Sonnet 5 | $0.00029 | $0.01348 |
| Haiku 4.5 | $0.00015 | $0.00674 |
Grade B, and why
axiom scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Take the key. Write it to `~/.claude/settings.json`'s `env` block under `AXIOM_API_KEY`. Tell the user to restart Claude Code for it to pick up. **Don't store the key anywhere else** — settings.json is the canonical loca How it starts
The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Axiom builder skill
You build axioms in two formats, chosen at runtime based on the user's intent:
- No-code axiom (JSON) — an
AutomationTemplatesaved to the user's Axiom account, runs in the dashboard, schedulable. - Coded axiom (
@axiom_ai/apiJavaScript) — a Node script the user runs from their own code.
You can also run a saved axiom (trigger it, poll for results) and hand one off to the Chrome extension for local preview/edit. These five capabilities are encoded as workflows in workflows/ — see references/workflows-index.md for the full registry.
Before you produce anything, decide which workflow fits. If the user's intent is ambiguous, ask one clarifying question.
Step −1 — Check for a newer skill version (once per conversation)
The first time the axiom skill activates in a conversation, run the update check via the skill's bundled script. Use the absolute path — the skill's base directory was announced when this skill loaded ("Base directory for this skill: "). The bash tool's CWD won't always match the skill directory, so a relative path will fail.
node "<SKILL_BASE_DIR>/scripts/check-for-updates.js"
Replace <SKILL_BASE_DIR> with the absolute path you were given at skill activation.
If it prints a line starting with UPDATE_AVAILABLE, surface a one-line note to the user before continuing with their request:
Heads up: skill v<latest> is available (you're on v<current>). Run
/plugin marketplace update axiom-skillsthen/reload-pluginsto upgrade. I'll continue with your current request — let me know if you'd rather upgrade first.
If the script prints nothing, proceed silently.
Don't re-run the check in the same conversation. Track that you've already done it in your conversation memory; users will get annoyed by repeated "heads up" messages. The script never errors out (it always exits 0); if the upstream probe failed for any reason — no gh, no network, repo not reachable — the script stays silent and you proceed.
What ships with it
60 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.
- examples/coded/login-then-extract.js 841 B runs code
- examples/coded/parallel-sessions.js 671 B runs code
- examples/coded/simple-scrape.js 615 B runs code
- examples/no-code/loop-through-sheet.json 9.3 KB
- examples/no-code/scheduled-daily.json 5.5 KB
- examples/no-code/scrape-and-write-sheet.json 8.4 KB
- examples/no-code/visit-example.json 3.4 KB
- references/account-setup.md 5.4 KB
- references/action-vocabulary.json 143 KB
- references/automation-template-schema.json 13 KB
- references/automation-template-schema.md 6.0 KB
- references/axiom-api-method-allowlist.json 703 B
- references/axiom-api-method-blocklist.json 388 B
- references/axiom-api-surface.md 3.7 KB
- references/decision-tree.md 2.6 KB
- references/docs/_index.json 106 KB
- references/docs/account/account.md 2.6 KB
- references/docs/account/create-account.md 1.1 KB
- references/docs/account/index.md 1.0 KB
- references/docs/account/subscription.md 2.3 KB
- references/docs/code-tool/create-scripts.md 2.2 KB
- references/docs/code-tool/dashboard.md 1.1 KB
- references/docs/code-tool/index.md 2.6 KB
- references/docs/code-tool/playground.md 1.2 KB
- references/docs/code-tool/run-reports.md 1.3 KB
- references/docs/code-tool/running-scripts.md 1.9 KB
- references/docs/code-tool/samples/data-entry.md 1.8 KB
- references/docs/code-tool/samples/index.md 754 B
- references/docs/code-tool/samples/navigate-to-page.md 1.2 KB
- references/docs/code-tool/token-generation.md 963 B
- references/docs/developer-hub/api/authentication.md 4.0 KB
- references/docs/developer-hub/api/cdp/index.md 5.9 KB
- references/docs/developer-hub/api/index.md 7.6 KB
- references/docs/developer-hub/api/mcp/build-your-own-server-python.md 4.1 KB
- references/docs/developer-hub/api/mcp/build-your-own-typescript.md 5.6 KB
- references/docs/developer-hub/api/mcp/desktop-app-server.md 5.6 KB
- references/docs/developer-hub/api/mcp/index.md 2.2 KB
- references/docs/developer-hub/api/mcp/register-with-claude.md 3.9 KB
- references/docs/developer-hub/api/programmatic-signup.md 8.6 KB
- references/docs/developer-hub/api/quickstart.md 6.1 KB
- references/docs/developer-hub/api/reference/data-payload.md 3.0 KB
- references/docs/developer-hub/api/reference/endpoints.md 2.6 KB
- references/docs/developer-hub/api/reference/errorcodes.md 5.4 KB
- references/docs/developer-hub/api/reference/index.md 1.0 KB
- references/docs/developer-hub/api/reference/responses.md 3.6 KB
- references/docs/developer-hub/api/run-automations/check-run-status.md 4.2 KB
- references/docs/developer-hub/api/run-automations/index.md 909 B
- references/docs/developer-hub/api/run-automations/list-automations.md 2.0 KB
- references/docs/developer-hub/api/run-automations/pass-input-data.md 4.1 KB
- references/docs/developer-hub/api/run-automations/run-reports.md 3.5 KB
- references/docs/developer-hub/api/run-automations/stop-a-run.md 3.9 KB
- references/docs/developer-hub/api/run-automations/trigger-an-automation.md 4.4 KB
- references/docs/developer-hub/api/run-automations/webhooks-from-a-step.md 3.8 KB
- references/docs/developer-hub/api/step-functions/click-and-drag.md 2.1 KB
- references/docs/developer-hub/api/step-functions/click-engagement-button.md 1.7 KB
- references/docs/developer-hub/api/step-functions/click-multiple.md 1.7 KB
- references/docs/developer-hub/api/step-functions/click.md 2.2 KB
- references/docs/developer-hub/api/step-functions/close-a-session.md 2.6 KB
- references/docs/developer-hub/api/step-functions/date-picker.md 2.4 KB
- references/docs/developer-hub/api/step-functions/enter-text.md 3.1 KB
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 · 407 lines · 146 tokens per session scan B c8ebf8cf04b3
axiom is a skill published in the GitHub repository axiom-browser-automation/claude-skill (4 stars, last pushed 1mo ago), licensed ISC. It adds 146 tokens to every session and 6,742 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
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.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
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…