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 agentmods add skills/postman-devrel/postman-claude-code-plugin/deploy-flownpx skills add Postman-Devrel/postman-claude-code-plugin --skill deploy-flowgit clone --depth 1 https://github.com/Postman-Devrel/postman-claude-code-pluginWhat 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 | $0.00050 | $0.00630 |
| Opus 5 | $0.00025 | $0.00315 |
| Sonnet 5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
deploy-flow 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 2d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Postman Flows assistant that deploys Flows using the Postman CLI. Deploying makes a flow triggerable and returns its Trigger URL.
The command this wraps
POSTMAN_CLI_SOURCE=claude-code-plugin postman flows deploy <flowId> --path </path> [options]
Options:
-p, --path <path>— required URL path for the trigger (e.g./checkout)-t, --timeout <timeout>— HTTP session timeout, 5000ms–60000ms (default10000ms)-a, --auth— enable authentication on the trigger
Step 1: Resolve the flow ID
If given a name rather than a 24-char ID, resolve it with the list-flows skill (ask which workspace if unknown; disambiguate on multiple matches).
Step 2: Propose a trigger path and CONFIRM
Deploy requires a URL path. Propose a sensible default derived from the flow name:
- "Checkout" →
/checkout - "Nightly Report" →
/nightly-report
Confirm the path and the deploy action with the user before running — deploy is mutating and requires explicit confirmation.
Ask about authentication only if relevant ("Should the trigger require auth?"). Add --auth only if they say yes.
Step 3: Deploy
Show the exact command, then run it after confirmation:
POSTMAN_CLI_SOURCE=claude-code-plugin postman flows deploy 12345-67890-abcdef --path /checkout
Report back:
- the resulting Trigger URL
- whether the trigger is enabled. If the CLI notes the trigger is off, tell the user and offer to enable it:
(enabling is also a state change → confirm first).POSTMAN_CLI_SOURCE=claude-code-plugin postman flows update 12345-67890-abcdef --trigger on
Example report:
Deployed the Checkout flow.
Trigger URL: https://<host>/checkout
Trigger: enabled
Step 4: Hand back to trigger (if part of deploy-then-trigger)
If deploying was requested so the user could run the flow, hand control back to the trigger-flow skill to fire it and report the Run ID + status + response — completing the deploy-then-trigger journey in one conversation.
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.
- 2d ago First seen · 65 lines · 50 tokens per session scan A 2cf42ceb9496
deploy-flow is a skill published in the GitHub repository Postman-Devrel/postman-claude-code-plugin (38 stars, last pushed 27d ago), licensed Apache-2.0. It adds 50 tokens to every session and 630 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
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?"…
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步(architecture-sync)。OpenCode / Claude / Codex / Cursor 通用。.
taiyi-diagram-c4
TaiyiForge 辅助 — 从代码反推 C4 架构文档(Observed/Inferred 分层 · Mermaid 真源)。OpenCode / Claude / Codex / Cursor 通用。.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.