copilot-dev: Command for Claude Code

.github/prompts/api-endpoint-review.prompt.md

api-endpoint-review is a command for Claude Code, GitHub Copilot from timothywarner/copilot-dev. It costs 16 tokens per session (1,527 once invoked), scanned A, original, MIT.

A checklist for reviewing a REST API endpoint, a web address that accepts or returns data, for correctness, security, error handling, and common practices.

In plain words
What is it for?
It is for reviewing endpoint code and reporting each check as pass, fail, or not applicable, with fixes for failures.
Why use it?
It helps reveal unsafe input handling, weak errors, and other problems before an endpoint is released.

Command for Claude CodeGitHub Copilot

Written for Claude Code and GitHub Copilot: argument-hint in frontmatter, but also a Copilot chat mode or prompt. Also seen: model in frontmatter.

This is timothywarner/copilot-dev's own configuration. It tells Claude Code and GitHub Copilot how to work on copilot-dev 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 copilot-dev configures →

Reuse

Borrowing it

Nothing to install: this file belongs to timothywarner/copilot-dev. 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/timothywarner/copilot-dev/main/.github/prompts/api-endpoint-review.prompt.md
Clone the repo
git clone --depth 1 https://github.com/timothywarner/copilot-dev

Made for: Claude Code, GitHub Copilot.

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 api-endpoint-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/timothywarner/copilot-dev/api-endpoint-review/github.svg)](https://agentmods.dev/commands/timothywarner/copilot-dev/api-endpoint-review)
Your own site
<a href="https://agentmods.dev/commands/timothywarner/copilot-dev/api-endpoint-review"><img src="https://agentmods.dev/badge/commands/timothywarner/copilot-dev/api-endpoint-review/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 api-endpoint-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/timothywarner/copilot-dev/api-endpoint-review"><img src="https://agentmods.dev/badge/commands/timothywarner/copilot-dev/api-endpoint-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,527 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 $0.00016 $0.01527
Opus 5.5 $0.00006 $0.00611
Sonnet 5.5 $0.00003 $0.00305
Haiku 4.5 $0.00002 $0.00153

Measured 1mo ago against content hash 06de0a2a9d3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

api-endpoint-review 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 1mo 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.

.github/prompts/api-endpoint-review.prompt.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perform a thorough review of the REST API endpoint in ${selection}.

If no code is selected, ask the user to paste the endpoint handler they want reviewed.


Review checklist

Work through each section systematically. For each item, state: PASS, FAIL, or N/A, followed by a brief explanation and (for FAILs) a concrete fix.


1. Input validation

  • Are all path parameters, query parameters, and request body fields validated before use?
  • Is validation done with a schema library (Zod, Pydantic, Joi, marshmallow) — not ad-hoc if checks?
  • Are unknown fields rejected or stripped (no mass-assignment vulnerability)?
  • Are field types, lengths, and formats enforced (e.g., email regex, ID must be UUID)?

What to look for:

// FAIL — no validation, trusting raw input
app.post('/users', (req, res) => {
  db.insert(req.body)  // dangerous: any fields accepted
})

// PASS — validate with Zod before touching the database
const CreateUserSchema = z.object({
  email: z.string().email(),
  name: z.string().min(1).max(100),
  role: z.enum(['admin', 'viewer'])
})

app.post('/users', (req, res) => {
  const parsed = CreateUserSchema.safeParse(req.body)
  if (!parsed.success) return res.status(400).json({ error: parsed.error.flatten() })
  db.insert(parsed.data)
})

2. Authentication and authorization

  • Is the endpoint protected by an authentication middleware (JWT verification, session check, API key)?
  • Is authorization checked — not just "is the user logged in" but "does THIS user own THIS resource"?
  • Are admin-only endpoints guarded with a role check?
  • Are anonymous requests rejected with 401 (not 403)?

What to look for:

// FAIL — endpoint readable by any authenticated user, even ones who don't own the resource
app.get('/users/:id/private-data', authMiddleware, async (req, res) => {
  const data = await db.getPrivateData(req.params.id)  // no ownership check!
  return res.json(data)
})

// PASS — verify the requesting user owns the resource
app.get('/users/:id/private-data', authMiddleware, async (req, res) => {
  if (req.user.id !== req.params.id && req.user.role !== 'admin') {
    return res.status(403).json({ error: 'Forbidden' })
  }
  const data = await db.getPrivateData(req.params.id)
  return res.json(data)
})

Read the full file on GitHub · 189 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. 1mo ago First seen · 189 lines · 16 tokens per session scan A 06de0a2a9d3a

Subscribe to this mod's changes

api-endpoint-review is a command published in the GitHub repository timothywarner/copilot-dev (46 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,527 once invoked, about $0.0001 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 2026-09-20.