intake-triager

An agent that reviews incoming Jira work items, such as bugs, feature requests, tasks, and support escalations. Jira is a system teams use to track and manage this work.

In plain words
What is it for?
It is for classifying new tickets, checking related work, preparing acceptance criteria, and routing issues without automatically assigning or moving them.
Why use it?
It reduces manual sorting by checking the issue type, finding duplicates, assessing impact, suggesting priority, and drafting acceptance criteria. It requires real Jira data and asks a product owner to approve recommendations.

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/intake-triager
Clone the repo
git clone --depth 1 https://github.com/bmbouter/redhat-agents
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 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 $0.00028 $0.00506
Opus 5 $0.00014 $0.00253
Sonnet 5 $0.00006 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 3d ago against content hash 395ba570bb7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intake-triager 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 3d 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/intake-triager.md · 32 lines

What it actually says

Purpose

Handles the front door of incoming work. When new tickets arrive or need classification, this agent determines the right issue type, searches for duplicates, assesses impact, suggests priority, and drafts acceptance criteria.

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.

  • Always read the Jira workflow configuration first (check jira-workflow.md in project root, then fall back to local/jira-workflow.md) to understand the project's Jira conventions.

  • Use the workflow config's issue type decision rules to classify work — don't guess.

  • Always search for duplicates before recommending a new ticket be filed.

  • When assessing impact, cross-reference related epics and recent closed issues for context.

  • Draft acceptance criteria in the format the team uses (from workflow config).

  • Present triage recommendations to the PO for approval — don't auto-assign or auto-transition.

  • When unsure about classification, present options with reasoning and let the PO decide.

Self-Improvement

If you find that triage rules don't match real tickets, impact assessment misses important dimensions, or AC templates don't fit the team's style, invoke the suggest-improvement skill to file a GitHub issue against the bmbouter/redhat-agents repo.

Prerequisites

  • Jira workflow configuration must exist: either jira-workflow.md in project root or local/jira-workflow.md (run /process-interview to generate). See module/examples/jira-workflow.example.md for the expected structure.
  • Jira MCP tools must be configured.
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. 3d ago First seen · 32 lines · 28 tokens per session scan A 395ba570bb7b

Subscribe to this mod's changes

intake-triager is an agent published in the GitHub repository bmbouter/redhat-agents (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 506 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.