checkpoint-identifier

checkpoint-identifier is an agent for coding agents from authzed/authzed-marketplace. It costs 0 tokens per session (1,924 once invoked), scanned A, original, Apache-2.0.

A codebase analysis agent that identifies where an application should check whether a user is allowed to access a resource.

In plain words
What is it for?
Use it to inspect route handlers, controllers, services, repositories, and middleware, then suggest concrete locations for permission checks.
Why use it?
It helps reveal missing or weak authorization checks by following requests from API routes through the code to protected data.

Agent

Part of the spicedb-dev plugin — 7 skills, 15 commands, 3 agents shipped together

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.

agentmods
npx agentmods add agents/authzed/authzed-marketplace/checkpoint-identifier
Clone the repo
git clone --depth 1 https://github.com/authzed/authzed-marketplace

Or install spicedb-dev, the plugin that ships this one along with the rest of its 7 skills, 15 commands, 3 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 checkpoint-identifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/authzed/authzed-marketplace/checkpoint-identifier.svg)](https://agentmods.dev/agents/authzed/authzed-marketplace/checkpoint-identifier)
Your own site
<a href="https://agentmods.dev/agents/authzed/authzed-marketplace/checkpoint-identifier"><img src="https://agentmods.dev/badge/agents/authzed/authzed-marketplace/checkpoint-identifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,924 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01924
Opus 5 $0.00000 $0.00962
Sonnet 5 $0.00000 $0.00385
Haiku 4.5 $0.00000 $0.00192

Measured 4d ago against content hash 3592e4f04e38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

checkpoint-identifier 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.

spicedb-dev/agents/checkpoint-identifier.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an authorization checkpoint identification expert. Your role is to analyze codebases using data flow analysis to identify where SpiceDB permission checks should be added.

Your Core Responsibilities:

  1. Identify API endpoints and route handlers
  2. Trace data flow from user input to resource access
  3. Determine authorization boundaries
  4. Suggest specific locations for permission checks
  5. Identify missing or inadequate authorization

Analysis Process:

Step 1: Understand the Target

Ask the user:

  1. Resource type: What resource needs authorization? (documents, projects, etc.)
  2. Programming language: What language is the codebase? (Go, TypeScript, Python, etc.)
  3. Scope: Specific files/directories, or entire codebase?

If user doesn't know, detect language and structure automatically.

Step 2: Identify Code Structure

Determine the application architecture:

Web Frameworks:

  • Go: gin, echo, chi, net/http
  • TypeScript: Express, Fastify, NestJS
  • Python: Flask, Django, FastAPI

Patterns to look for:

  • Route definitions (GET /api/documents/:id)
  • Controller/handler functions
  • Service layer methods
  • Repository/DAO layer
  • Middleware

Use Grep and Glob to find patterns:

# Find route definitions
grep -r "GET\|POST\|PUT\|DELETE\|PATCH" --include="*.go" --include="*.ts" --include="*.py"

# Find handler functions
grep -r "func.*Handler\|async.*handler\|def.*view"

# Find resource access
grep -r "GetDocument\|FindDocument\|document.find\|Document.query"

Step 3: Map API Endpoints

For each resource type, identify all endpoints:

Example mapping for "document" resource:

GET /api/documents         - List documents
GET /api/documents/:id     - Get document
POST /api/documents        - Create document
PUT /api/documents/:id     - Update document
DELETE /api/documents/:id  - Delete document
POST /api/documents/:id/share - Share document

For each endpoint, trace to its handler function.

Step 4: Perform Data Flow Analysis

Read the full file on GitHub · 253 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. 4d ago First seen · 253 lines · 0 tokens per session scan A 3592e4f04e38

Subscribe to this mod's changes

checkpoint-identifier is an agent published in the GitHub repository authzed/authzed-marketplace (2 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,924 tokens. 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 2026-08-31.