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/logesh-works/postman-mcp/promptgit clone --depth 1 https://github.com/logesh-works/postman-mcpWrote 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/commands/logesh-works/postman-mcp/prompt)<a href="https://agentmods.dev/commands/logesh-works/postman-mcp/prompt"><img src="https://agentmods.dev/badge/commands/logesh-works/postman-mcp/prompt.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00572 |
| Opus 5 | $0.00000 | $0.00286 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
prompt 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 5d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/postman:prompt: natural-language sync
The natural-language front-end to the sync engine. Describe what you want in plain
English and Claude figures out what to sync and how, then runs it through the same
diff-then-confirm gate as every other command. This replaces the old --prompt flag that
used to hang off the individual sync commands.
Usage
/postman:prompt "<what to sync and how, in plain English>"
Examples:
/postman:prompt "add error responses to the payments routes"
/postman:prompt "give every endpoint an X-Request-Id header"
/postman:prompt "sync the login endpoint and rewrite its description as a Stripe-style architect"
/postman:prompt "add the standard 4xx/5xx error set to the whole codebase"
How it works
- Claude picks the scope. From the instruction it chooses what to analyze — one route, a file/module/dir, recent changes, or the whole codebase — and the target. If the scope is ambiguous it asks you before doing anything.
- Claude folds the "how" directly into what it authors. Concrete asks — extra error
responses, headers, an edited description, example values, a persona — go straight
into the
collection.json/metadata.jsonClaude writes, cited the same way as any other content. Anything added that isn't backed by a citation (an extra example response, say) is written without one and shows as unverified in the diff, honestly. - Validate, verify, diff, confirm, write. Claude calls
sync_fileswithconfirmoff first; the MCP server validates the collection, re-verifies every citation, and returns the diff preview. You're asked "Write to Postman? [y/n]"; only onydoes it write.
What stays deterministic
The MCP tools have no prompt parameter and run no model. Your instruction is read
by Claude, which writes it directly into the collection — there's no separate patch
object the server merges. What the server does is fixed regardless of the instruction:
validate the collection is well-formed, re-read and re-hash every citation, ground every
claimed field against the real code, and diff the result. Route identity, citations, and
field grounding come from your code and stay unaffected by what the instruction says.
Whatever content the instruction adds shows up in the diff before any write, so the
confirm gate fully covers prompt-driven content. See the
Prompt & skill layer.
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.
- 5d ago First seen · 49 lines · 0 tokens per session scan A 9683d3adcbf1
prompt is a command published in the GitHub repository logesh-works/postman-mcp (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 572 tokens. 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.