Agent skill

Har Derived API Client

by templetongroup in templetongroup/radiant

Turn a website's hidden API into a reusable plain-HTTP client — drive the browser once, capture the XHR/fetch calls, then rebuild and verify a script.

MITAuto-check passedBackend & APIs

Install Har Derived API Client

skills CLI
$ npx skills add templetongroup/radiant --skill har-derived-api-client -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install templetongroup/radiant har-derived-api-client --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/templetongroup/radiant.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/har-derived-api-client .claude/skills/har-derived-api-client && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
har-derived-api-client
GitHub stars
113
Token cost
~730 tokens
SKILL.md length
418 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Turn a website's hidden API into a reusable plain-HTTP client — drive the browser once, capture the XHR/fetch calls, then rebuild and verify a script.

  • Works in 5 steps: Operate. browser_navigate to the site,… → Capture + derive. Call browser_network… → Build. Write a small, self-contained… → …
  • Backend & APIs work in your project
  • SKILL.md covers When to use, Procedure and Watch out for
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Har Derived API Client is an agent skill from templetongroup/radiant. Turn a website's hidden API into a reusable plain-HTTP client — drive the browser once, capture the XHR/fetch calls, then rebuild and verify a script.

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs. The repository describes itself as: A local coding harness for Mac. Chat with coding agents across cloud and local models, watch every tool call in a live activity feed, and drive a real terminal — in one window… The licence is MIT.

When your agent uses it

  • Backend & APIs work in your project

Example prompts

  • “/har-derived-api-client”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Operate. browser_navigate to the site, then use browser_click /
  2. Capture + derive. Call browser_network (optionally with a filter
  3. Build. Write a small, self-contained client into the workspace (prefer
  4. Verify. Run the client and confirm its response matches what the site
  5. Reuse. The result is one verified HTTP client the user (or an agent,

What it can do on your machine

Read from SKILL.md and the folder at commit 94838ca. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Har Derived API Client loads about 730 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 418 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~730

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from templetongroup/radiant at commit 94838ca, republished under its MIT licence (© templetongroup). 418 words, ~730 tokens.

Download SKILL.mdSave it as .claude/skills/har-derived-api-client/SKILL.md (or your agent's skills folder).
name
har-derived-api-client
description
Turn a website's hidden API into a reusable plain-HTTP client — drive the browser once, capture the XHR/fetch calls, then rebuild and verify a script.

Website → reusable API client

Some sites have no public API, but the page itself calls internal JSON endpoints (XHR / fetch). Instead of driving the browser every time (slow and brittle), use the browser once to discover those endpoints, then rebuild the one you need as a plain HTTP request you can call forever from a script, CLI, or cron.

When to use

The user wants to pull data from, or repeat an action on, a website that has no official API — search results, a feed, prices, a list, a submit. Requires the computer toggle on (browser control) and a vision-capable model.

Procedure

  1. Operate. browser_navigate to the site, then use browser_click / browser_type / browser_key to perform the exact action once (run the search, load the page, submit the form). Do the real thing — the goal is to make the site fire its internal request.

  2. Capture + derive. Call browser_network (optionally with a filter substring) to list the XHR/fetch JSON calls the page just made. Find the one whose response sample contains the data the user wants. Note its method, URL (and query params), request body, and which headers it carries.

  3. Build. Write a small, self-contained client into the workspace (prefer Python requests, or curl) that recreates just that request:

    • Keep only the headers the endpoint actually needs — usually accept, content-type, and any auth/token header. Drop browser noise.
    • Never hard-code secrets. Any header shown as [present — sensitive] (cookies, authorization, CSRF/API tokens) is required but must be read from an environment variable or a local, git-ignored file — not pasted into the script.
    • Parse the JSON response into exactly the fields the user asked for.
  4. Verify. Run the client and confirm its response matches what the site returned in step 2. Only call it done once it reproduces the data headlessly.

  5. Reuse. The result is one verified HTTP client the user (or an agent, cron job, or CLI) can call directly — no browser needed.

Show full SKILL.md (95 more words)Show less

Watch out for

  • This is capture-and-replay, not a bypass. Do not attempt to defeat authentication, CAPTCHAs, rate limits, or bot detection. If the endpoint is gated that way, stop and tell the user.
  • Captured requests can contain live cookies and tokens. Keep them out of shared code, logs, and commits; use env vars. Treat the capture as secret.
  • Endpoints and tokens change. If the client starts failing (401/403 or a changed shape), re-capture from the live site.
  • Respect the site's Terms of Service and robots restrictions; only automate what the user is authorized to access.

© templetongroup, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/har-derived-api-client of templetongroup/radiant.

Open the folder on GitHubat commit 94838ca

Compare with similar skills

Har Derived API Client next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Har Derived API Client compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Har Derived API Client this skilltempletongroup/radiant113—~730Automated safety check: PassMIT
Configuring Horizoncoollabsio/coolify63k4 repos~898Automated safety check: PassMIT
Nestjs Best Practicesrolling-scopes/rsschool-app10k6 repos~1.2kAutomated safety check: PassMIT
Sub2API AdminWei-Shaw/sub2api44k1 repos~717Automated safety check: PassLGPL-3.0
Firecrawl Build Onboardingfirecrawl/firecrawl190k1 repos~1.4kAutomated safety check: NotesISC
Obsidian BasesAtmosphere/atmosphere3.8k22 repos~3.2kAutomated safety check: PassApache-2.0

Similar skills

  • Configuring Horizon

    coollabsio/coolify

    A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.

    63k GitHub starsUsed in 4 repos~898 tokens
    Backend & APIsAuto-check passed
  • Nestjs Best Practices

    rolling-scopes/rsschool-app

    NestJS best practices and architecture patterns for building production-ready applications.

    10k GitHub starsUsed in 6 repos~1.2k tokens
    Backend & APIsAuto-check passed
  • Sub2API Admin

    Wei-Shaw/sub2api

    Manages a Sub2API deployment from the command line: accounts, redeem and invitation codes, groups, proxies, imports, exports and raw admin API calls.

    44k GitHub starsUsed in 1 repo~717 tokens
    Backend & APIsAuto-check passed
  • Firecrawl Build Onboarding

    firecrawl/firecrawl

    Gets Firecrawl working in a project: signs you in through the browser, saves FIRECRAWL_API_KEY to .env and picks the first SDK or REST path.

    190k GitHub starsUsed in 1 repo~1.4k tokens
    Backend & APIsAuto-check: notes
  • Obsidian Bases

    Atmosphere/atmosphere

    Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries.

    3.8k GitHub starsUsed in 22 repos~3.2k tokens
    Backend & APIsAuto-check passed
  • Fortify Development

    coollabsio/coolify

    ACTIVATE when the user works on authentication in Laravel. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 4 repos~1.9k tokens
    Backend & APIsAuto-check passed

More from templetongroup/radiant

All 9 skills in this repo
  • Design System

    templetongroup/radiant

    A skill your agent uses to generate or audit design systems, check visual consistency, and review PRs that touch styling.

    113 GitHub stars~775 tokensUpdated 3 days ago
    Auto-check passed
  • Master Design

    templetongroup/radiant

    Design, redesign, build, audit, polish, and production-verify exceptional interfaces across web, mobile, and native apps.

    113 GitHub stars~2.9k tokensUpdated 3 days ago
    Auto-check passed
  • Tinystruct Patterns

    templetongroup/radiant

    Expert guidance for developing with the tinystruct Java framework.

    113 GitHub stars~3k tokensUpdated 3 days ago
    Auto-check passed
  • Agent Payment X402

    templetongroup/radiant

    Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets.

    113 GitHub stars~2.7k tokensUpdated 3 days ago
    Auto-check passed
  • Motion UI

    templetongroup/radiant

    Production-ready UI motion system for React/Next.js. An agent skill from templetongroup/radiant.

    113 GitHub stars~3.5k tokensUpdated 3 days ago
    Auto-check passed
  • Plan Orchestrate

    templetongroup/radiant

    Read a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit ready-to-paste /orchestrate custom prompts.

    113 GitHub stars~4.5k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Har Derived API Client

What does Har Derived API Client do?

Turn a website's hidden API into a reusable plain-HTTP client — drive the browser once, capture the XHR/fetch calls, then rebuild and verify a script. Har Derived API Client is an agent skill from templetongroup/radiant. Turn a website's hidden API into a reusable plain-HTTP client — drive the browser once, capture the XHR/fetch calls, then rebuild and verify a script.

When should I use Har Derived API Client?

Har Derived API Client fits situations like: backend & APIs work in your project.

How do I install Har Derived API Client in Claude Code?

Run `npx skills add templetongroup/radiant --skill har-derived-api-client -a claude-code`. Or copy the skill folder (skills/har-derived-api-client in templetongroup/radiant) into .claude/skills/har-derived-api-client in your project. Claude Code loads it when a task matches its description.

How do I install Har Derived API Client in Codex?

Run `npx skills add templetongroup/radiant --skill har-derived-api-client -a codex`. Or copy the skill folder (skills/har-derived-api-client in templetongroup/radiant) into .agents/skills/har-derived-api-client in your project. Codex loads it when a task matches its description.

Can I use Har Derived API Client in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add templetongroup/radiant --skill har-derived-api-client -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/har-derived-api-client, .gemini/skills/har-derived-api-client, .github/skills/har-derived-api-client and .opencode/skills/har-derived-api-client in your project.

What does Har Derived API Client need to run?

SKILL.md names no scripts, command-line tools or credentials: Har Derived API Client is instructions for the agent only. Our summary lists: Python 3.

Does Har Derived API Client access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Har Derived API Client safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Har Derived API Client use?

Har Derived API Client is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Har Derived API Client use?

About 730 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Har Derived API Client?

Skills that share tags, products or a category with Har Derived API Client: Configuring Horizon (coollabsio/coolify, 63k stars), Nestjs Best Practices (rolling-scopes/rsschool-app, 10k stars), Sub2API Admin (Wei-Shaw/sub2api, 44k stars) and Firecrawl Build Onboarding (firecrawl/firecrawl, 190k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Har Derived API Client?

templetongroup (a GitHub user) maintains it in templetongroup/radiant, which has 113 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 6, 2026.

Source: templetongroup/radiant on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.