agentmods.dev

aisense-free-tools

aisense-free-tools is a skill for Claude Code, Codex from aisenseapi/aisense-free-public-rest-apis. It costs 50 tokens per session (1,183 once invoked), scanned A, original, MIT.

A skill for using the free AI SENSE MCP server, a remote service with utility and workflow tools. It covers QR codes, HTML-to-PDF conversion, hashing, time zones, temporary storage, webhooks, queues, and decisions.

In plain words
What is it for?
It is for configuring AI SENSE and using its tools for document conversion, data handling, webhook capture, workflow coordination, and rule-based decisions.
Why use it?
It explains how to connect the server and select the appropriate tool without building each small utility yourself.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

not rated 1repo changed 9d ago A scan 50 tokens original MIT

Good fit It is for configuring AI SENSE and using its tools for document conversion, data handling, webhook capture, workflow coordination, and rule-based decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aisenseapi/aisense-free-public-rest-apis/aisense-free-tools
View source ↗ aisenseapi/aisense-free-public-rest-apis aisense.no
Install

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.

Any agent
npx skills add aisenseapi/aisense-free-public-rest-apis --skill aisense-free-tools
Clone the repo
git clone --depth 1 https://github.com/aisenseapi/aisense-free-public-rest-apis

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for aisense-free-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/aisenseapi/aisense-free-public-rest-apis/aisense-free-tools/github.svg)](https://agentmods.dev/skills/aisenseapi/aisense-free-public-rest-apis/aisense-free-tools)
Your own site
<a href="https://agentmods.dev/skills/aisenseapi/aisense-free-public-rest-apis/aisense-free-tools"><img src="https://agentmods.dev/badge/skills/aisenseapi/aisense-free-public-rest-apis/aisense-free-tools/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.

agentmods 80×15 button for aisense-free-tools

Your own site · 80×15
<a href="https://agentmods.dev/skills/aisenseapi/aisense-free-public-rest-apis/aisense-free-tools"><img src="https://agentmods.dev/badge/skills/aisenseapi/aisense-free-public-rest-apis/aisense-free-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01183
Opus 5.5 $0.00020 $0.00473
Sonnet 5.5 $0.00010 $0.00237
Haiku 4.5 $0.00005 $0.00118

Measured 9d ago against content hash 3b0dce4aac2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aisense-free-tools 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 9d 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.

integrations/clawhub-skill/aisense-free-tools/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI SENSE free tools

A remote MCP server at https://aisenseapi.com/mcp with 79 tools, run by AI SENSE AS in Oslo. No account, no key, no session ID. Every address has 5000 requests a day across all tools, so call when there is a need and do not poll.

Setup, once

This skill cannot add the server for you. Add it with the OpenClaw CLI (its documentation runs saved-server edits with the Gateway stopped) or in Settings, MCP, Add server while the Gateway runs:

openclaw mcp add aisense --url https://aisenseapi.com/mcp --transport streamable-http
openclaw mcp doctor aisense --probe

The probe lists the tools the server advertises. If it lists none, the server is not reachable from this machine; stop and tell the user.

Which tool for what

Names are the server's own. Prefer the first match, and read a tool's description before calling it with real data.

  • A typed decision from facts and rules: decide. Send the facts as state and questions of type yes_no, choice or scale with weighted rules; the answer carries a probability, a confidence, an action of act, review or hold, and the rules that held. Rules compute on the server; the optional model mode sends the state to a decision model.
  • Receive a webhook and know what arrived: create_webhook_capture gives an update URL for the sender and a read URL; read_webhook_capture returns the first request that hit it (method, headers, client address, body). One request per capture, 24 hours.
  • Hand bytes or JSON to another step or machine: store_temporary_data and read_temporary_data (JSON or text), store_file and read_stored_file (files). 24 hours, an optional download limit, 80 MB per address per day. Never secrets or personal data.
  • QR codes: create_qr_code (text in, PNG as Base64 out), read_qr_code (image in, text out).
  • A PDF from HTML: html_to_pdf. Markdown and HTML: html_markdown_convert. JSON and CSV: json_check, json_csv_convert, match_tables.
  • Time: get_current_time, convert_timestamp, time_formats, list_timezones.
  • Hashing, encoding, random: hash_data, verify_hash, encode_data, generate_uuid, generate_random, slugify_text, jwt_token.
  • Images: process_image (convert, resize, compress, metadata, strip EXIF, palette).
  • Work between agents: create_agent_queue with enqueue_agent_queue_job, claim_agent_queue_job and ack_agent_queue_job; acquire_lease for one owner at a time; create_heartbeat and ping_heartbeat for liveness; create_agent_inbox and read_agent_inbox for a mail address; create_agent_handoff and create_agent_run for handing work on; create_agent_wake to resume after an outside event; create_human_approval to ask a person.
  • A secret read once: create_one_time_secret stores an encrypted envelope the client made; never send plaintext or keys to it.
  • Network and validation: lookup_network, validate_email, validate_value, shorten_url, create_dns_name, service_health.

Read the full file on GitHub · 94 lines

Changes

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.

  1. 9d ago Changed 3b0dce4aac2b
  2. 10d ago First seen · 94 lines · 50 tokens per session scan A 890735bb6d34

Subscribe to this mod's changes

aisense-free-tools is a skill published in the GitHub repository aisenseapi/aisense-free-public-rest-apis (1 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 1,183 once invoked, about $0.0002 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 2026-11-04.

Building agentsProductivityclaude-skillclaude-skillsfree-apifree-apisjavascriptllm-tools
Related

aisense-free-tools compared with skills from other repositories

aisense-free-tools next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aisense-free-toolsaisenseapi/aisense-free-public-rest-apisSkill13d agoMITA50Claude Code, Codex
sorting-groceriesoaustegard/claude-skillsSkill395todayMITA65Claude Code
tree-sittingoaustegard/claude-skillsSkill395todayMITA184Claude Code
mapping-codebasesoaustegard/claude-skillsSkill395todayMITA99Claude Code, Codex
treatRuya-AI/cozempicSkill4304mo agoMITA25Claude Code
reloadRuya-AI/cozempicSkill4304mo agoMITA16Claude Code
handoff-by-caiokaragos/ai-skills-by-caioSkill27mo agononeA120Claude Code, Codex