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 agentmods add skills/hesedcasa/sdkck/extract-apinpx skills add hesedcasa/sdkck --skill extract-apigit clone --depth 1 https://github.com/hesedcasa/sdkckWrote 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/hesedcasa/sdkck/extract-api)<a href="https://agentmods.dev/skills/hesedcasa/sdkck/extract-api"><img src="https://agentmods.dev/badge/skills/hesedcasa/sdkck/extract-api.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.04177 |
| Opus 5 | $0.00043 | $0.02089 |
| Sonnet 5 | $0.00017 | $0.00835 |
| Haiku 4.5 | $0.00009 | $0.00418 |
Grade C, and why
extract-api scanned grade C with 2 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 4d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore --> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: WebFetch, Read, Write, Agent, Bash(sdkck:*), Bash(gh:*), Bash(curl:*), Bash(jq:*), Bash(node:*), Bash(npm:*), Bash(python3:*) How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract API endpoints from any source and import them into sdkck as executable CLI commands.
Overview
This skill reads API documentation from three source types:
- GitHub repositories (public): scans for OpenAPI specs, Postman collections, GraphQL schemas, README, and docs files
- HTTP/HTTPS documentation URLs: fetches single or multi-page doc sites; probes for spec/collection/schema files; POSTs introspection query to live GraphQL endpoints
- Local files: reads OpenAPI JSON/YAML, Postman collections, GraphQL SDL/introspection JSON, markdown, HTML, or plain text
When an existing OpenAPI spec, Postman collection, or GraphQL schema is found it is used directly — no extraction needed. Otherwise, API endpoints are extracted from the documentation and an OpenAPI 3.0 JSON document is generated. Either way, the result is imported via sdkck api import.
Usage
/extract <source> [--name <name>]
| Argument | Description |
|---|---|
<source> |
GitHub URL, HTTP/HTTPS URL, or local file path |
--name |
Override the API name (default: derived from source) |
Examples:
/extract https://petstore3.swagger.io/api/v3/openapi.json --name petstore
/extract https://github.com/stripe/openapi --name stripe
/extract https://developers.notion.com/reference/intro
/extract https://docs.github.com/en/rest --name github
/extract https://api.example.com/graphql --name myapi
/extract ./my-workspace.postman_collection.json --name myapi
/extract ./my-project/api-docs.md --name myapi
/extract ./introspection.json --name myapi
/extract ./schema.graphql --name myapi
Workflow
Step 1 — Parse arguments
Extract from the user's input:
SOURCE: the GitHub URL, HTTP URL, or file pathNAME: value of--nameif provided; otherwise derive from the source:- GitHub URL → repository name (e.g.
stripe-openapi) - HTTP URL → domain slug (e.g.
docs-github-com) - Local file → filename without extension
- GitHub URL → repository name (e.g.
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.
- 4d ago First seen · 261 lines · 86 tokens per session scan C 233934b4bf6e
extract-api is a skill published in the GitHub repository hesedcasa/sdkck (9 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 4,177 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pir-action-tracker
Parses Post-Incident Review (PIR) pages in a Confluence space, fetches live status from referenced Jira tickets, updates action item tables with current status and due dates, marks completed PIRs with a visual closure panel, and surfaces any overdue actions for follow-up. Designed for Customer Success, Support, and…
atls
ALL Atlassian work — Jira, Confluence, Bitbucket on Server/DC (지라/컨플루언스/비트버킷). Load BEFORE the first atls command. Without this body you WILL guess atls conventions wrong: JQL/CQL is positional, -f is --md-file not --format, managed push differs from page update, exit 5 = stale-version. TRIGGER: Jira, Confluence…
pm-skills
Use when coordinating project-delivery work across the 8 project-management sub-skills — sprint/velocity analytics, portfolio health, Jira/JQL, Confluence, Atlassian admin, templates, meeting analysis, team comms. Triggers on 'our sprints feel off', 'project health report', 'audit our Jira permissions', 'when will it…
atlassian-cli
Use when working with Jira or Confluence from command line, including authentication, searching issues with JQL, bulk operations, sprint reports, or creating/updating work items using acli.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
search-company-knowledge
Search across company knowledge bases (Confluence, Jira, internal docs) to find and explain internal concepts, processes, and technical details. When an agent needs to: (1) Find or search for information about systems, terminology, processes, deployment, authentication, infrastructure, architecture, or technical…