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 commands/postman-devrel/postman-claude-code-plugin/trigger-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 | $0.00023 | $0.00371 |
| Opus 5 | $0.00012 | $0.00186 |
| Sonnet 5 | $0.00005 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
trigger-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.
What it actually says
Trigger a deployed Postman Flow from natural language, using the Postman CLI. Follow the trigger-flow skill.
Inputs (from the user's message)
- The flow (a 24-char ID, or a name to resolve via
list-flows) - Any inputs / query params / headers / scenario
- The workspace ID (ask if a name needs resolving and you don't have it)
Steps
- Resolve the flow ID (use
list-flowsif given a name; disambiguate multiple matches; ask for the workspace if unknown). - Build the flags from natural language:
-i k=v,-q k=v,--headers k=v,-s "<scenario>". - Show the command, then run it:
POSTMAN_CLI_SOURCE=claude-code-plugin postman flows trigger <flowId> -i amount=4200 - Report the Run ID, HTTP status, and response body.
- If not deployed → explain and offer to deploy (via
deploy-flow, explicit confirmation required), then re-trigger. If the trigger is disabled → offerpostman flows update <flowId> --trigger on(confirm), then trigger. - On a non-2xx response → surface status + body and offer
get-flow-run --run-id <id>for per-block detail.
Always prefix CLI calls with POSTMAN_CLI_SOURCE=claude-code-plugin. Reuse existing postman login credentials — never authenticate twice. Confirm before any mutating action (deploy, enable trigger).
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 · 25 lines · 23 tokens per session scan A 57890fd62510
trigger-flow is a command published in the GitHub repository Postman-Devrel/postman-claude-code-plugin (38 stars, last pushed 27d ago), licensed Apache-2.0. It adds 23 tokens to every session and 371 once invoked, about $0.0001 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 commands, from other repositories
refine-title
深度分析 Issue 或 PR 内容，并将其标题重构为 Conventional Commits 格式.
warden-cost
Dollar accounting — what does each active rule actually save, in money? Translates the token-measured verdict into dollars using a price table and the agent's own token-type mix, with a per-session net and a break-even. Read-only; spends no tokens.
routine
Execute one maintenance routine defined in scv/routines/ .md (task + guardrails + exit-criteria contract), or list defined routines. SCV never schedules — pair with host features like /loop or cron yourself. Use whenever the user asks to run a recurring maintenance task, or asks what routines exist — not only when…
incident
Live incident response — intake a Sentry issue, stack trace, or symptom; gate mitigate-first vs root-cause-first; keep a UTC timeline. Use when production is broken RIGHT NOW; for the after-action write-up alone, use /orc:postmortem.
t800-onboard
Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.
t800-bootstrap
Запускайте один раз при установке плагина или для новичка в чате.