workflow-tracer

workflow-tracer is a command for Claude Code from sigistry/marketplace. It costs 10 tokens per session (3,540 once invoked), scanned A, original, MIT.

A codebase analysis command that maps the business areas, important objects, and relationships in an unfamiliar application. It also identifies the main technologies, databases, APIs, and entry points.

In plain words
What is it for?
Use it to discover domains such as users, orders, or payments, locate their definitions, and explain how those entities relate.
Why use it?
It gives developers a starting map when the codebase has little documentation or its purpose is unclear.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter.

Part of the legacy-analyzer plugin — 5 commands shipped together

Good fit Use it to discover domains such as users, orders, or payments, locate their definitions, and explain how those entities relate.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sigistry/marketplace/workflow-tracer
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.

Clone the repo
git clone --depth 1 https://github.com/sigistry/marketplace

Made for: Claude Code.

Or install legacy-analyzer, the plugin that ships this one along with the rest of its 5 commands.

Wrote 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.

agentmods badge for workflow-tracer

README.md
[![agentmods](https://agentmods.dev/badge/commands/sigistry/marketplace/workflow-tracer/github.svg)](https://agentmods.dev/commands/sigistry/marketplace/workflow-tracer)
Your own site
<a href="https://agentmods.dev/commands/sigistry/marketplace/workflow-tracer"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/workflow-tracer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for workflow-tracer

Your own site · 80×15
<a href="https://agentmods.dev/commands/sigistry/marketplace/workflow-tracer"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/workflow-tracer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00010 $0.03540
Opus 5 $0.00005 $0.01770
Sonnet 5 $0.00002 $0.00708
Haiku 4.5 $0.00001 $0.00354

Measured 6d ago against content hash d9646169b70a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

workflow-tracer 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 6d 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.

plugins/legacy-analyzer/commands/workflow-tracer.md · 543 lines

How it starts

The opening of the file, as written. The whole thing — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Tracer Command

Trace a complete end-to-end workflow through the codebase, showing exactly what happens step-by-step from a business perspective.

Objective

Given a workflow name, feature, or user action (e.g., "user registration", "checkout process", "order approval"), trace the complete execution path through all layers of the codebase and explain what happens at each step in business terms.

Step 1: Workflow Identification

If User Provided a Workflow Name

  • Search for relevant API endpoints, event handlers, or functions matching that name
  • Identify the entry point (API endpoint, CLI command, scheduled job, event handler)

If No Workflow Specified

  • List common workflows found in the codebase:
    • User authentication/registration
    • CRUD operations for main entities
    • Payment/transaction processing
    • Data import/export
    • Approval/review workflows
    • Notification/alert processes
    • Scheduled batch operations

Ask the user which workflow to trace.

Step 2: Entry Point Analysis

Document how the workflow is initiated:

## Workflow: [Workflow Name]

### Entry Point
**Trigger**: [API call / User action / Scheduled job / Event / etc.]
**Location**: `file_path:line_number`

**For API Endpoint**:
- **Method**: [GET/POST/PUT/DELETE]
- **Path**: `/api/path/to/endpoint`
- **Authentication**: [Required/Optional]
- **Request Format**:
```json
{
  "field1": "value",
  "field2": 123
}

For Event:

  • Event Name: [event.name]
  • Event Source: [Where event is published from]
  • Event Payload: [Data structure]

For Scheduled Job:

  • Schedule: [cron expression or frequency]
  • Trigger Conditions: [When it runs]

## Step 3: Step-by-Step Trace

Follow the execution path through all code layers:

### Tracing Methodology
1. Start from entry point
2. Follow function calls
3. Track data transformations
4. Identify decision points
5. Note database operations
6. Track external API calls
7. Follow to completion or error states

Read the full file on GitHub · 543 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. 6d ago First seen · 543 lines · 10 tokens per session scan A d9646169b70a

Subscribe to this mod's changes

workflow-tracer is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 5d ago), licensed MIT. It adds 10 tokens to every session and 3,540 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 2026-09-03.