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/syncapigit clone --depth 1 https://github.com/logesh-works/postman-mcpWhat 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 | $0.00000 | $0.00951 |
| Opus 5 | $0.00000 | $0.00476 |
| Sonnet 5 | $0.00000 | $0.00190 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
syncapi 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 yesterday.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/postman:syncapi: sync one API
The most surgical of the five commands. It syncs exactly one route and touches nothing else. Every other command is just a different way of picking which routes go through the same validate → verify → diff → confirm → write pipeline this one uses directly.
Usage
/postman:syncapi <function_name | "METHOD /route" | "pasted code"> [--into path] [--confirm]
For free-form instructions (add error responses, headers, an edited description, a
persona, …), use /postman:prompt instead.
Targeting
You can identify the route three ways:
- Function name, like
create_payment - Route string, like
"POST /payments/refund" - Pasted code, a snippet of the handler
If the target is ambiguous (the same name matches more than one route), the command lists the candidates and asks you to be specific. It never guesses.
Flags
| Flag | Effect |
|---|---|
--into <path> |
Folder inside the collection where the request lands, for example payments or auth/oauth. Missing folders are created automatically. If omitted, falls back to config.defaultInto, which defaults to the collection root. No folder gets inferred from the route or function name. |
--confirm |
Only required when targeting a collection other than the configured default. A safety rail, not something you'll normally need. |
Example
/postman:syncapi create_payment --into payments
Collection: Acme Backend
Plan: 1 new · 0 modified
[NEW] POST /payments → payments ✓ verified (app/payments.py:12)
Write to Postman? Re-run with confirm=true to apply.
Each line is labelled ✓ verified (the citation matches your code), ~ stale (the code
moved since it was cited), or ⚠ CITATION DOES NOT MATCH CODE — so you can see which
requests are backed by real code before you say yes. An endpoint that fails verification
is excluded from the write unless you name it explicitly.
What happens, step by step
- Find the endpoint. Claude uses the repository index to locate
create_paymentand read the exact code it needs — the handler, its request/response types, and its route registration — without reading the project unbounded. - Author the request. Claude writes a complete Postman request (method, path,
params, body, auth, responses) into
collection.json, plus afile:linecitation for every claimed fact inmetadata.json. - Validate and verify. The MCP server checks the collection is well-formed, re-reads every cited line to confirm it matches what Claude claimed, and grounds every claimed request/response field against the real DTO/model class.
- Diff. The server reads the live collection, matches
POST /paymentsbyMETHOD + normalized path, and renders the before/after preview — a new request if no match is found, resolving--into paymentsto a folder (creating it if needed). - Confirm. The diff is always shown. A non-default collection target additionally
needs
--confirm. - Write. Merge into the collection JSON and
PUT /collections/{uid}. - Record. Update
lastUpdateinpostman/config.json. Claude shows the write result and stops; no further analysis or follow-on commentary.
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.
- yesterday First seen · 87 lines · 0 tokens per session scan A e5b130c42020
syncapi 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 951 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.