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.
npx agentmods add agents/bmbouter/redhat-agents/intake-triagergit clone --depth 1 https://github.com/bmbouter/redhat-agentsWhat 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 | $0.00028 | $0.00506 |
| Opus 5 | $0.00014 | $0.00253 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
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.
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.mdin project root, then fall back tolocal/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.mdin project root orlocal/jira-workflow.md(run/process-interviewto generate). Seemodule/examples/jira-workflow.example.mdfor the expected structure. - Jira MCP tools must be configured.
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.
- 3d ago First seen · 32 lines · 28 tokens per session scan A 395ba570bb7b
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.