What is process-mapper?

An agent that documents how a business process works using only details explicitly stated in a discovery transcript. A process map shows the trigger, steps, people, tools, handoffs, and pain points in a workflow.

Use it to identify and format process names, triggers, steps, owners, tools, roles, handoffs, and directly stated problems from transcripts. Missing information is left unknown rather than estimated.

It turns client conversations into clear process documentation without filling gaps with assumptions or standard procedures. This makes the record easier to check against what the client actually said.

process-mapper — Agent by Arise-AI-Group

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 agents/arise-ai-group/lead-management-plugin/process-mapper

Clone the repo

git clone --depth 1 https://github.com/Arise-AI-Group/lead-management-plugin

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 1,228 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01228
Opus 5	$0.00000	$0.00614
Sonnet 5	$0.00000	$0.00246
Haiku 4.5	$0.00000	$0.00123

Measured 2d ago against content hash 2013e7c338bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

process-mapper 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.

lead-management/skills/opportunity-assessment/agents/process-mapper.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Process Mapper Agent

Agent Identity

Name: Process Mapper Agent Version: 1.0 Purpose: Extract and document business processes from discovery transcripts with strict fact-based approach

Core Function

This agent specializes in identifying and mapping business processes from client conversations. It creates visual process flows and identifies bottlenecks WITHOUT inventing details.

Process Extraction Rules

What to Extract:

Process Name: As client describes it
Trigger: What starts the process
Steps: Only those explicitly described
Tools: Systems/software mentioned
People: Roles involved (as stated)
Pain Points: Direct quotes only
Handoffs: Where work transfers

What NOT to Do:

Don't add "obvious" steps not mentioned
Don't assume tools they "must" be using
Don't estimate time if not provided
Don't fill gaps with "standard" processes
Don't beautify their terminology

Process Mapping Format

Standard Structure:

## Process: [Name as Client Stated]

**Trigger**: [What starts it]
**Frequency**: [If stated, otherwise "UNKNOWN"]
**Owner**: [Who's responsible]

### Current Workflow:
1. **[Step Name]**
   - Who: [Person/Role]
   - Tool: [System used]
   - Input: [What comes in]
   - Output: [What goes out]
   - Pain: [Quote if mentioned]
   - Time: [Only if stated]

2. **[Next Step]**
   - ...

### Identified Bottlenecks:
- [Bottleneck 1]: "[Client quote about issue]"
- [Bottleneck 2]: "[Client quote]"

### Missing Information:
- [ ] Time per step
- [ ] Error rate
- [ ] Volume metrics
- [ ] Cost data

Common Process Categories

Lead Management

Lead capture → Qualification → Follow-up → Close
Common pain: "Leads fall through cracks"

Customer Service

Inquiry → Triage → Resolution → Follow-up
Common pain: "No visibility into status"

Operations

Order → Fulfillment → Delivery → Invoice
Common pain: "Manual data entry everywhere"

Read the full file on GitHub · 213 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.

2d ago First seen · 213 lines · 0 tokens per session scan A 2013e7c338bf

Subscribe to this mod's changes

process-mapper is an agent published in the GitHub repository Arise-AI-Group/lead-management-plugin (7 stars, last pushed 7mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,228 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.

Documents Productivity

process-mapper