curl-debug

curl-debug is a skill for Claude Code from hg-pyun/claude-code-marketplace. It costs 195 tokens per session (2,798 once invoked), scanned A, original, MIT.

A debugging method for investigating a failing cURL API request by running the request and tracing its response through the codebase. cURL is a command-line tool for making web requests.

In plain words
What is it for?
Use it when a user provides a cURL command with a bug or error and wants to find what caused the failure and where it occurs.
Why use it?
It connects the visible API error to the code responsible for it, reducing unfocused searching. It prioritizes clues such as stack traces, error messages, status codes, URLs, request fields, and response structure.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the AskUserQuestion tool.

Part of the dev-tools plugin — 11 skills, 1 command, 15 agents shipped together

Good fit Use it when a user provides a cURL command with a bug or error and wants to find what caused the failure and where it occurs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hg-pyun/claude-code-marketplace/curl-debug
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 hg-pyun/claude-code-marketplace --skill curl-debug
Clone the repo
git clone --depth 1 https://github.com/hg-pyun/claude-code-marketplace

Made for: Claude Code.

Or install dev-tools, the plugin that ships this one along with the rest of its 11 skills, 1 command, 15 agents.

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 curl-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/hg-pyun/claude-code-marketplace/curl-debug.svg)](https://agentmods.dev/skills/hg-pyun/claude-code-marketplace/curl-debug)
Your own site
<a href="https://agentmods.dev/skills/hg-pyun/claude-code-marketplace/curl-debug"><img src="https://agentmods.dev/badge/skills/hg-pyun/claude-code-marketplace/curl-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,798 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00195 $0.02798
Opus 5 $0.00097 $0.01399
Sonnet 5 $0.00039 $0.00560
Haiku 4.5 $0.00019 $0.00280

Measured 8d ago against content hash 1f3915a441c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

curl-debug 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 8d 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.

name: curl-debug
plugins/dev-tools/skills/curl-debug/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Use_When>

  • User shares a cURL command alongside a bug question ("이 요청 500 나는데 왜?", "this curl returns 500, help me debug")
  • User invokes /curl-debug <cURL>
  • A failing API request needs to be traced back to source code
  • User wants a structured trace from observable symptom to root cause </Use_When>

<Do_Not_Use_When>

  • User just wants to execute a cURL without debugging intent — run it directly
  • User is asking about cURL syntax conceptually
  • User is sharing cURL for documentation purposes
  • No cURL is provided and the user wants pure codebase exploration — use other tools </Do_Not_Use_When>

<Why_This_Exists> Tracing an API bug from "this curl returns 500" to "this exact line in this exact file" is a high-frequency activity that benefits from a deterministic flow. Without a structured procedure, callers waste time grepping random strings. This skill applies signal priority (stack trace > error message > error code > URL path > body fields > response structure) so the strongest available signal is followed first, and stops as soon as What/Where/Why are answered. </Why_This_Exists>

<Execution_Policy>

  • Always run the user's actual cURL — do not skip Step 1 unless the network is unreachable.
  • Trace by signal priority (table below). Stream each step as you go.
  • Route Step 3 by signal grade: grade-1 signals (stack trace with direct file:line, or the 404 short-circuit) are traced inline by the main session via Read/Grep; weaker, indirect signals with real competing hypotheses delegate to the tracer agent.
  • Halt as soon as you can answer What / Where / Why.
  • Never apply fixes — present fix options for the user to choose from.
  • For non-trivial proposed fixes, optionally delegate to the reviewer agent for severity-rated review (see Step 4). </Execution_Policy>

Print the result. For long responses, summarize the key parts.

On network error: present likely causes (server down, DNS failure, etc.) and AskUserQuestion whether to retry. Proceed with URL-path-based code tracing regardless — the code exists even if the server is down.

Read the full file on GitHub · 179 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. 8d ago First seen · 179 lines · 195 tokens per session scan A 1f3915a441c0

Subscribe to this mod's changes

curl-debug is a skill published in the GitHub repository hg-pyun/claude-code-marketplace (2 stars, last pushed 2mo ago), licensed MIT. It adds 195 tokens to every session and 2,798 once invoked, about $0.0010 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 skills, from other repositories

printing-press-amend

Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…

mvanhorn/cli-printing-press · 222 tokens

convex-performance-audit

Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.

openclaw/clawhub · 38 tokens

convex-insights

Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

openclaw/clawhub · 45 tokens

ssl-proxy-troubleshoot

Systematic workflow for troubleshooting SSL/proxy connectivity issues with government websites.

HKUDS/OpenSpace · 20 tokens

diagnose-backend-bug

Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…

QoderAI/better-harness · 87 tokens

axiom-networking

Use when implementing or debugging ANY network connection, API call, or socket. Covers URLSession, Network.framework, NetworkConnection, connection diagnostics.

CharlesWiltgen/Axiom · 33 tokens