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/postman-claude-code-plugin --skill api-discoverygit clone --depth 1 https://github.com/Postman-Devrel/postman-claude-code-pluginWrote 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/postman-claude-code-plugin/api-discovery)<a href="https://agentmods.dev/skills/postman-devrel/postman-claude-code-plugin/api-discovery"><img src="https://agentmods.dev/badge/skills/postman-devrel/postman-claude-code-plugin/api-discovery/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/postman-claude-code-plugin/api-discovery"><img src="https://agentmods.dev/badge/skills/postman-devrel/postman-claude-code-plugin/api-discovery.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00124 | $0.01134 |
| Opus 5.5 | $0.00050 | $0.00454 |
| Sonnet 5.5 | $0.00025 | $0.00227 |
| Haiku 4.5 | $0.00012 | $0.00113 |
Grade A, and why
api-discovery 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Discovery
Overview
Two unconnected datasets, so pick by data source, not question shape:
search/context→ Postman-authored artifacts someone saved in Postman (collections, requests, specs, mocks, workspaces). Matches text; doesn't reason. "Does something named/shaped like X exist?"context-graph ask→ a separately-populated engineering service graph (built from repo/traffic scanning, not Postman content) — natural-language Q&A over discovered services and the dependency edges between them. "What depends on billing-api?" — architecture questionssearchstructurally can't answer, since there's no keyword for a dependency edge.
A miss in one says nothing about the other (see Critical Rule 1) — never
fall back to the Context Graph just because a search came back empty, or
vice versa.
search
search <type> <query> where type is requests, collections,
workspaces, flows, specs, mocks, environments, or documents.
Default --ownership organization only searches inside your org — pass
external or all before concluding "no API for this exists," since a
partner or public API published outside the org is invisible at the
default scope. --filter "method=POST AND workspaceId=ws-123" narrows
further; see reference/search_filters.md for
the full filter field and operator syntax per element type.
context-graph
context-graph ask "<question>" --wait is the one to reach for
interactively — it blocks and prints the answer. Without --wait, ask
returns an id immediately and status <askId> checks on it later (exit
code 3 while still running) — useful for a question expected to take a
while, or from a script polling on its own cadence. The query runs against
the team derived from the API key; there's no workspace/team selection.
--max-steps caps how much reasoning the service does per question.
The answer is generated, not retrieved verbatim — verify with a re-ask or narrower query before acting on it for anything consequential (Critical Rule 3), the same way any AI-generated claim gets checked before it drives a decision.
What ships with it
1 file 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 · 95 lines · 124 tokens per session scan A cceca5cf3b1f
api-discovery is a skill published in the GitHub repository Postman-Devrel/postman-claude-code-plugin (41 stars, last pushed 22d ago), licensed Apache-2.0. It adds 124 tokens to every session and 1,134 once invoked, about $0.0005 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.
Other skills, from other repositories
postman
Full API lifecycle management through Postman. Sync OpenAPI specs to collections, generate typed client code, run API tests, create mock servers, publish documentation, audit security against OWASP Top 10, and discover APIs across workspaces. Requires the Postman MCP Server. Use this skill when the user mentions…
postman-api-readiness
Analyze any API for AI agent compatibility. Scans OpenAPI specs across 8 pillars (48 checks), scores agent-readiness 0-100, and provides prioritized fix recommendations. Use this skill when the user asks: "Is my API agent-ready?", "Scan my API", "Analyze my OpenAPI spec", "What's wrong with my API for AI agents?"…
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
qveris
Access third-party professional data and tools through QVeris: find services, review supported scope when needed, call them, and generate production REST code. Use when existing tools are insufficient, a provider is unknown, comparison or fallback is needed, or the user requests QVeris.
qveris-cli
Use QVeris CLI to find and call third-party professional data and tools when existing tools are insufficient, a provider is unknown, comparison or fallback is needed, or the user requests QVeris.