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 skills add Postman-Devrel/agent-skills --skill postmangit clone --depth 1 https://github.com/Postman-Devrel/agent-skillsWrote 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/postman-devrel/agent-skills/postman)<a href="https://agentmods.dev/skills/postman-devrel/agent-skills/postman"><img src="https://agentmods.dev/badge/skills/postman-devrel/agent-skills/postman/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.
<a href="https://agentmods.dev/skills/postman-devrel/agent-skills/postman"><img src="https://agentmods.dev/badge/skills/postman-devrel/agent-skills/postman.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 5.1 | $0.00111 | $0.05232 |
| Opus 5.5 | $0.00044 | $0.02093 |
| Sonnet 5.5 | $0.00022 | $0.01046 |
| Haiku 4.5 | $0.00011 | $0.00523 |
Grade A, and why
postman scanned grade A 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 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST https://<mock-id>.mock.pstmn.io/pets -d '{"name":"Buddy"}' Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://<mock-id>.mock.pstmn.io/pets How it starts
The opening of the file, as written. The whole thing — 567 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postman Agent Skill
Full API lifecycle management through the Postman MCP Server. Sync specs, generate code, run tests, create mocks, publish docs, and audit security.
Version: 2.0.1 Requires: Postman MCP Server
Prerequisites
This skill requires the Postman MCP Server to be configured. The MCP server exposes 111+ tools for interacting with Postman workspaces, collections, specs, environments, mocks, monitors, and more.
Setup check: Call getAuthenticatedUser via MCP. If it succeeds, you're connected. If it fails, walk through Setup below.
Important: MCP Tool Behavior
Before using the workflows below, be aware of these behaviors:
getWorkspacesreturns ALL workspaces. For large organizations this can be 300KB+. If you already have a workspace ID, usegetWorkspace(workspaceId)directly instead.getCollectiondefault response is a lightweight map withitemRefs(folder/request tree). This is efficient for discovery. Only usemodel=fullwhen you need complete request/response bodies, and be aware it can exceed 300KB for large collections. Prefer targetedgetCollectionRequestandgetCollectionResponsecalls for specific endpoints.getTaggedEntitiesreturns 404 for missing tags, not an empty array. Handle this gracefully. Tag functionality may require an Enterprise plan.runCollectionreturns aggregate results only (total requests, passed, failed, duration). It does NOT return per-request detail or error messages. For debugging specific failures, examine individual requests withgetCollectionRequestandgetCollectionResponseafter the run.searchPostmanElementsonly searches the PUBLIC Postman network, not private workspaces. Always search private workspace first withgetCollections.
Setup
If MCP tools are not available or getAuthenticatedUser fails:
- Get a Postman API key:
- Go to https://postman.postman.co/settings/me/api-keys
- Click "Generate API Key", name it "Claude Code"
- Copy the key (starts with PMAK-)
What ships with it
2 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.
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.
- 1mo ago First seen · 567 lines · 111 tokens per session scan A 2442d98f539e
postman is a skill published in the GitHub repository Postman-Devrel/agent-skills (17 stars, last pushed 21d ago), licensed MIT. It adds 111 tokens to every session and 5,232 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
api-mocking
Stands up a fake backend that behaves like a real API — from a collection or an OpenAPI spec, running locally or pushed to Postman's cloud for a durable URL — plus request-time scenario and status-code overrides for testing failure paths. Use when the user asks to "mock this API," "create a mock server," "fake the…
api-testing
Runs tests against an API from the command line — a single ad-hoc request, a full collection of pm.test assertions, or matching real captured app traffic against a collection contract. Use when the user asks to "test this endpoint," "run this collection," "check the API still works," or "verify my app's requests match…
go-service-idioms
This skill should be used when the user asks to "write a Go function", "implement this in Go", "structure this Go service", "add error handling in Go", "handle context cancellation in Go", "write a Go worker pool", "add a table-driven test", "review this Go code for idioms", or otherwise writes or reviews Go…
flows
Runs, deploys, and debugs Postman Flows from the command line — executing a flow file locally, triggering a deployed flow over its webhook, deploying one so it becomes callable, and tracing a failed run to the block that broke. Use when the user names a flow and an action ("run the Checkout flow", "deploy this flow"…
collection-schema-v3
The reference for the git-native v3 collection file format — one YAML file per request/folder/example under postman/collections/, plus postman/environments/. Read before writing, editing, or generating any file in either directory by hand, or before debugging a collection lint failure. Covers the HTTP…
bootstrap
Resolves the Postman CLI, authenticates, links the workspace, and records this repo's spec path, collections directory and workspace id. Use when the user asks to "set up Postman here", "connect this repo to Postman", "link this workspace", "authenticate with Postman", "postman login", or "run postman init" — and…