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/run-collectiongit 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 | $0.00008 | $0.00313 |
| Opus 5 | $0.00004 | $0.00156 |
| Sonnet 5 | $0.00002 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
run-collection 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
Run Postman collection tests to verify your API endpoints.
Step 1: Find Collections and IDs
List collection folders and look up their cloud IDs:
ls postman/collections/
cat .postman/resources.yaml
The cloudResources.collections section maps local collection paths to cloud IDs.
If no collections found, tell the user and stop. If one collection, use it directly. If multiple, list them and ask which to run.
Step 2: Run the Collection
Run by collection ID (from .postman/resources.yaml):
postman collection run <collection-id>
Common options:
# Stop on first failure
postman collection run <collection-id> --bail
# With request timeout
postman collection run <collection-id> --timeout-request 10000
# With environment
postman collection run <collection-id> -e ./postman/environments/<env-file>.json
# Override environment variable
postman collection run <collection-id> --env-var "base_url=http://localhost:3000"
Step 3: Parse and Report Results
Parse the CLI output for pass/fail counts, failed test names, error messages, and status codes.
Step 4: Handle Failures
If tests fail:
- Analyze error messages
- Read relevant source code
- Suggest fixes
- After fixes, re-run to verify
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 · 56 lines · 8 tokens per session scan A 3615c0b72e9e
run-collection 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 8 tokens to every session and 313 once invoked, about $0.0000 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
qa
Pre-PR quality gate — browser-driven QA for web changes with a mandatory evidence packet against a provisioned environment. No QA-passed claim without artifacts. Workspace-aware. For a quick behavioral check without the evidence packet, prefer the bundled /verify or /run.
gui-anything
Build a complete GUI harness for any software application.
validate
Validate a GUI harness against HARNESS.md standards and best practices.
refine
Expand and improve an existing GUI harness with additional coverage.
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
run-all-tests-and-fix
Execute the full test suite and systematically fix any failures, ensuring code quality and functionality. All test-related commands must pass before completion.