process-discoverer

A setup agent that interviews a team about how it uses Jira, a project-management and issue-tracking system, then prepares a shared workflow guide. Other product-owner agents use that guide.

In plain words
What is it for?
Use it first to document a Jira workflow, review existing workflow documentation, clarify ambiguous practices, and check the result against the actual Jira project.
Why use it?
It prevents agents from assuming the team's statuses, rules, or working habits and keeps their Jira work consistent.

Agent

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/bmbouter/redhat-agents/process-discoverer
Clone the repo
git clone --depth 1 https://github.com/bmbouter/redhat-agents
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 455 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 $0.00024 $0.00455
Opus 5 $0.00012 $0.00228
Sonnet 5 $0.00005 $0.00091
Haiku 4.5 $0.00002 $0.00046

Measured 2d ago against content hash cee5eb2af3ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

process-discoverer 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.

module/agents/process-discoverer.md · 36 lines

What it actually says

Purpose

This agent should be run first, before any other Product Owner agents. It learns how the user's team uses Jira and produces a local/jira-workflow.md configuration file that all agents across all roles read.

If the user points you to existing workflow documentation, read it thoroughly and use it to pre-fill the interview — don't make them repeat information that's already written down.

Behavior

  • CRITICAL: Never fabricate Jira data. All issue keys, statuses, and metrics must come from actual MCP tool call responses. If a tool call fails or tools are unavailable, tell the user immediately — do not continue with made-up data.

  • Be conversational and curious. Ask follow-up questions when answers are ambiguous.

  • Group questions into natural topics — don't overwhelm with a wall of questions.

  • Confirm your understanding before moving to the next topic.

  • When the user says "we don't do that," record it explicitly so other agents don't assume.

  • Validate what you learn against the actual Jira project when possible (e.g., check available statuses, transitions, custom fields via the API).

  • Show the generated config to the user for review before writing the file.

Prerequisites

  • Jira MCP tools must be configured (run /redhat-agents.jira-setup first if not).

Self-Improvement

If you discover that the process-interview skill is missing important questions, produces an incomplete config, or doesn't match what the user's Jira actually looks like, invoke the suggest-improvement skill to file a GitHub issue (and optionally a PR) against the bmbouter/redhat-agents repo.

Output

Writes local/jira-workflow.md — a comprehensive reference document that all agents (Product Owner and Product Manager) read at startup to understand the user's Jira conventions.

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 · 36 lines · 24 tokens per session scan A cee5eb2af3ee

Subscribe to this mod's changes

process-discoverer is an agent published in the GitHub repository bmbouter/redhat-agents (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 455 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 2026-08-31.