ed-fi-api-spec

ed-fi-api-spec is a skill for Claude Code, Codex from Ed-Fi-Exchange-OSS/Ed-Fi-SDK-for-AI-Assistants. It costs 94 tokens per session (708 once invoked), scanned A, original, Apache-2.0.

A searchable reference for Ed-Fi API resources and descriptor types, without loading the full OpenAPI specification. Ed-Fi is a standard for exchanging K–12 education data through APIs.

In plain words
What is it for?
Use it to look up concepts such as enrollment, attendance, grades, students, or parents and find the fields and paths needed to work with them.
Why use it?
It helps developers find the right resource, endpoint, required fields, references, and nested data without searching a very large specification.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to look up concepts such as enrollment, attendance, grades, students, or parents and find the fields and paths needed to work with them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ed-fi-exchange-oss/ed-fi-sdk-for-ai-assistants/ed-fi-api-spec
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 Ed-Fi-Exchange-OSS/Ed-Fi-SDK-for-AI-Assistants --skill ed-fi-api-spec
Clone the repo
git clone --depth 1 https://github.com/Ed-Fi-Exchange-OSS/Ed-Fi-SDK-for-AI-Assistants

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 ed-fi-api-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/ed-fi-exchange-oss/ed-fi-sdk-for-ai-assistants/ed-fi-api-spec/github.svg)](https://agentmods.dev/skills/ed-fi-exchange-oss/ed-fi-sdk-for-ai-assistants/ed-fi-api-spec)
Your own site
<a href="https://agentmods.dev/skills/ed-fi-exchange-oss/ed-fi-sdk-for-ai-assistants/ed-fi-api-spec"><img src="https://agentmods.dev/badge/skills/ed-fi-exchange-oss/ed-fi-sdk-for-ai-assistants/ed-fi-api-spec/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 ed-fi-api-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/ed-fi-exchange-oss/ed-fi-sdk-for-ai-assistants/ed-fi-api-spec"><img src="https://agentmods.dev/badge/skills/ed-fi-exchange-oss/ed-fi-sdk-for-ai-assistants/ed-fi-api-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 708 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 $0.00094 $0.00708
Opus 5.5 $0.00038 $0.00283
Sonnet 5.5 $0.00019 $0.00142
Haiku 4.5 $0.00009 $0.00071

Measured 4d ago against content hash 621e0726dde2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ed-fi-api-spec 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 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.

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.

skills/ed-fi-api-spec/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ed-Fi API spec lookup

A Markdown index of the Ed-Fi Resources and Descriptors API specifications (Data Standard 5.2, generated from the ODS/API 7.3 sandbox metadata). The full specifications are about 2.7 million tokens; a lookup here usually needs 8–10 thousand.

How to look something up

  1. Find the resource. Search references/index.md for the developer's term. Each line has the resource name, its collection path and the first sentence of its description, plus common synonyms ("Also: …"). If the first term finds nothing, try other wordings: singular and plural, the business term ("enrolled", "enrollment", "registration") and the Ed-Fi term ("association").
  2. Open only the resource files you need, under references/resources/<name>.md, where <name> is the plural collection name from the index (students.md, grades.md, studentSchoolAssociations.md). Each file has:
    • every field, marked yes when required, with its type, the fields to supply inside each ...Reference, and which fields are descriptors;
    • the fields of each nested collection (for example classPeriods in sections), with their own required flags;
    • the endpoints, including /deletes, /keyChanges and /partitions where they exist, and whether PUT can change the resource's identifying values (cascading key updates).
  3. For descriptor types, search references/descriptors.md. Descriptor values are data, not part of the spec: read them from the target API.

Don't open index.md and many resource files "just in case"; open what the task needs.

Limits

  • Data Standard 5.2 only. Paths are shown as in the spec (/ed-fi/students); build full URLs from the host's Discovery API (urls.dataManagementApi), which differs between ODS/API 7.x (.../data/v3/) and Ed-Fi API 8 (.../data/).
  • Host extensions are not included. Extensions appear only in each host's own metadata; regenerate this index from that host with eng/spec-knowledge-graph/generate.py (see its README in the repository).
  • No natural keys. The OpenAPI specification does not say which fields identify a record: a required reference may or may not be part of the identity. For a resource's natural key, use the Data Standard documentation or ask the host; don't infer it from the required fields.

Read the full file on GitHub · 44 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 44 lines · 94 tokens per session scan A 621e0726dde2

Subscribe to this mod's changes

ed-fi-api-spec is a skill published in the GitHub repository Ed-Fi-Exchange-OSS/Ed-Fi-SDK-for-AI-Assistants (1 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 708 once invoked, about $0.0004 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 2026-10-24.

Related

Other skills, from other repositories

api-onboarding

Reduce time-to-first-API-call (TTFAC) by optimizing every step of the developer onboarding journey. This skill covers authentication simplification, sandbox environments, interactive documentation, and identifying and eliminating common failure points.

sickn33/agentic-awesome-skills · 46 tokens

system-design-case-catalog

Answer classic system design problems as constraint-to-solution sketches and coach interview practice: URL shortener, rate limiter, news feed, chat, notification, autocomplete, crawler, unique id. Use for interview practice or naming the closest known shape for a new problem.

HoangNguyen0403/agent-skills-standard · 58 tokens

frontmcp-guides

Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…

agentfront/frontmcp · 157 tokens

kafka-guide-skill

A learning and design guide for Apache Kafka, a system that moves streams of messages between applications. It covers Kafka concepts, installation, producers, consumers, reliability, ordering, and choosing suitable business uses.

jiushiwon/wg-skills · 141 tokens

twitter-interviewer

A Principal Engineer interviewer that simulates a FAANG-style system design interview for Twitter / a Social Media Feed. Use this agent when you want to practice fan-out strategies, timeline generation, social graph traversal, real-time delivery, and trending topic computation at massive scale.

PrepLabsAI/InterviewMentor · 57 tokens

api-design-interviewer

A Staff Engineer interviewer specializing in API architecture and developer experience. Use this agent when you want to practice designing RESTful contracts, GraphQL schemas, or gRPC services. It will challenge you on pagination, idempotency, versioning, and API Gateway patterns to ensure your APIs are both scalable…

PrepLabsAI/InterviewMentor · 71 tokens