syncall

A Claude Code command that reads every route, controller, and model and synchronizes the whole project with a Postman collection. A Postman collection is a saved group of API requests and related documentation.

In plain words
What is it for?
Use it to populate a collection from scratch or update it after broad code changes; use the target-folder option to place all synced routes in one collection folder.
Why use it?
It reconciles an entire collection after initial setup or a large refactor, while showing a difference plan before writing changes.

Command

Install

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.

agentmods
npx agentmods add commands/logesh-works/postman-mcp/syncall
Clone the repo
git clone --depth 1 https://github.com/logesh-works/postman-mcp
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 625 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00625
Opus 5 $0.00000 $0.00313
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00063

Measured 2d ago against content hash 9dc4fc93a4af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

syncall 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.

docs/commands/syncall.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/postman:syncall: the whole codebase

Reads every route, controller, and model in the project and syncs all of it. Use it for first-time setup or after a big refactor. Always diffs first, same as every other write-capable command.

Usage

/postman:syncall [--into path]

For free-form instructions (add error responses, headers, a rewritten description, …), use /postman:prompt instead.

Flags

Flag Effect
--into <path> Folder inside the collection every synced route lands in. If omitted, falls back to config.defaultInto, which defaults to the collection root. There's no automatic per-route folder inference; every route in the run goes to the same target.

When to use it

  • First run after init, to populate an empty or partial collection from scratch.
  • After a refactor, to reconcile the collection with sweeping code changes.

For everyday work, prefer /postman:syncchanges. It's much cheaper because it only looks at what changed instead of re-reading the whole project.

Example

/postman:syncall

Collection: Acme Backend
Plan: 21 new · 2 modified

[NEW] POST /payments   → (root)   ✓ verified (app/payments.py:12)
[MODIFY] GET /orders/{id}   → (root)   ✓ verified (app/orders.py:40)
...

Write to Postman? Re-run with confirm=true to apply.

Every route in a run lands in the same target: the collection root by default, or --into <path> if you gave one. Each line is labelled ✓ verified, ~ stale, or ⚠ CITATION DOES NOT MATCH CODE so you can see at a glance which requests are backed by real code before you write anything.

!!! note "Routes removed from code" syncall doesn't currently mark a request deprecated just because the route behind it disappeared from the codebase — it only writes what it finds. Removing a stale request from the collection by hand is the workaround until this lands. Track it in ROADMAP.md.

Read the full file on GitHub · 64 lines

Changes

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.

  1. 2d ago First seen · 64 lines · 0 tokens per session scan A 9dc4fc93a4af

Subscribe to this mod's changes

syncall 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 625 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.