social-skills: Instructions file for Claude Code

CLAUDE.md

social-skills CLAUDE.md is an instructions file for Claude Code from jedi4ever/social-skills. It costs 2,426 tokens per session, scanned A, original, MIT.

Coding instructions for social-skills, a project that connects to search services and other external APIs and may read third-party web pages.

In plain words
What is it for?
They guide HTTP error handling, provider-specific error parsing, rate-limit checks, and maintenance of web-page scrapers.
Why use it?
They make API failures understandable and account for limits and changing website layouts instead of hiding errors or relying on fragile selectors.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code.

This is jedi4ever/social-skills's own configuration. It tells Claude Code how to work on social-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything social-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jedi4ever/social-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jedi4ever/social-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jedi4ever/social-skills

Made for: Claude Code.

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 social-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jedi4ever/social-skills/claude-md/github.svg)](https://agentmods.dev/instructions/jedi4ever/social-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jedi4ever/social-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/jedi4ever/social-skills/claude-md/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 social-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jedi4ever/social-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/jedi4ever/social-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,426 This file is loaded in full into every session.
When invoked 2,426 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02426 $0.02426
Opus 5 $0.01213 $0.01213
Sonnet 5 $0.00485 $0.00485
Haiku 4.5 $0.00243 $0.00243

Measured 10d ago against content hash 1570d467e85d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

social-skills CLAUDE.md scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- The in-sandbox upstream is healthy (in-sandbox curl returns 200)
CLAUDE.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

social-skills — repo conventions

Error handling for external APIs

Never swallow HTTP error bodies. Every external HTTP call in this repo (search providers, source fetchers, bridge clients) must surface the underlying API's error message, not just the status code. A bare HTTP 400 is a bug — the body almost always contains the real reason (rate limit hit, invalid parameter, expired key, tier exceeded).

Use core.HTTPErrorBody(resp) at every non-2xx branch:

if resp.StatusCode < 200 || resp.StatusCode >= 300 {
    return nil, fmt.Errorf("foo: HTTP %d: %s", resp.StatusCode, core.HTTPErrorBody(resp))
}

The helper reads up to 512 bytes, collapses whitespace to one line, and truncates to 256 chars. It's safe to call on any *http.Response and consumes the body (do not read again afterwards).

When an API has a structured error envelope worth parsing (X v2 returns {errors:[{message}]} or {title,detail}), add a provider-local decoder — see xsearch.decodeXError for the pattern. Generic providers should just use core.HTTPErrorBody.

Pre-flight known API limits

When a provider has a hard tier limit that produces a non-actionable error from the API, validate the request before sending and return a clear local error explaining the constraint. Example: X v2 recent search caps start_time to 7 days — xsearch.go rejects out-of-window opts.After with a message that names the constraint, instead of letting X return a bare HTTP 400.

Daytona preview-URL proxy is flaky for POST /fetch and /screenshot

The signed-URL proxy that fronts each Daytona sandbox port (5556-<id>.daytonaproxy01.net) returns intermittent HTTP 404 "Not found." on proxied POST requests, even when:

  • The in-sandbox upstream is healthy (in-sandbox curl returns 200)
  • The same external curl with the same token returns 200
  • The proxy's GET /status with the same token returns 200

Manifests as flaky /fetch and /screenshot through social-browser daemon --provider daytona. We've sunk hours debugging this multiple times — it is a Daytona-side issue, not ours. Don't re-investigate; instead:

Read the full file on GitHub · 218 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. 10d ago First seen · 218 lines · 2,426 tokens per session scan A 1570d467e85d

Subscribe to this mod's changes

social-skills CLAUDE.md is an instructions file published in the GitHub repository jedi4ever/social-skills (8 stars, last pushed 4mo ago), licensed MIT. It adds 2,426 tokens to every session, about $0.0121 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens