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.
git clone --depth 1 https://github.com/redhat-community-ai-tools/UnifAIWrote 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.
[](https://agentmods.dev/commands/redhat-community-ai-tools/unifai/pipeline)<a href="https://agentmods.dev/commands/redhat-community-ai-tools/unifai/pipeline"><img src="https://agentmods.dev/badge/commands/redhat-community-ai-tools/unifai/pipeline/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.
<a href="https://agentmods.dev/commands/redhat-community-ai-tools/unifai/pipeline"><img src="https://agentmods.dev/badge/commands/redhat-community-ai-tools/unifai/pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00000 | $0.04180 |
| Opus 5 | $0.00000 | $0.02090 |
| Sonnet 5 | $0.00000 | $0.00836 |
| Haiku 4.5 | $0.00000 | $0.00418 |
Grade A, and why
pipeline 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pipeline orchestrator. You drive a multi-agent development workflow through sequential phases. Each phase has a dedicated skill file that you read and apply.
Usage
/pipeline <task or Jira ticket> → full mode (Phase 1)
/pipeline full <Jira ticket ID or URL> → full mode, fetch ticket via MCP
/pipeline full <free-text task prompt> → full mode (Phase 1)
/pipeline full <path-to-design-file> → full mode, skip to Phase 2
/pipeline design-only <Jira ticket or prompt> → design only
/pipeline design-only --adr <prompt> → design only, write ADR file
/pipeline design-and-review <Jira ticket or prompt> → design + review with revision loops
/pipeline implement <path-to-approved-design> → implementation + code review + QA
/pipeline review-only <path-to-design-file> → review an existing design
/pipeline code-review-only [files/folders] → code review on changes
/pipeline qa-only [files/folders] → run QA on changes
/pipeline arch-review [files/folders] → architecture review on changes
/pipeline review [files/folders] → arch + code review (shared scout, parallel judges)
/pipeline debug <error description or log file path> → structured debug session
Mode Dispatch Table
This is the authoritative mapping. Do NOT infer phases from mode names.
| Mode | Keyword | Phases | Skill files (in order) |
|---|---|---|---|
| 1 | full |
1→2→3→4→5 | designer.md → design-reviewer.md → coder.md → code-reviewer.md → qa.md |
| 2 | design-only |
1 | designer.md |
| 3 | design-and-review |
1→2 | designer.md → design-reviewer.md |
| 4 | implement |
3→4→5 | coder.md → code-reviewer.md → qa.md |
| 5 | review-only |
2 | design-reviewer.md |
| 6 | code-review-only |
4 | code-reviewer.md |
| 7 | qa-only |
5 | qa.md |
| 8 | debug |
6 | debugger.md |
| 9 | arch-review |
9 | arch-reviewer.md |
| 10 | review |
9+4 | _scout.md → arch-reviewer.md + code-reviewer.md (parallel) |
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.
- 12d ago First seen · 295 lines · 0 tokens per session scan A 74bb0f82dec4
pipeline is a command published in the GitHub repository redhat-community-ai-tools/UnifAI (44 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,180 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 2026-08-30.
Other commands, from other repositories
dashboard-session-abort-all
Abort multiple running sessions (asks which). Usage /dashboard:session-abort-all.
dashboard-session-tell
Send a prompt to another session. Usage /dashboard:session-tell.
dashboard-session-rename
Rename a session. Usage /dashboard:session-rename.
dashboard-session-unhide
Unhide a previously hidden session. Usage /dashboard:session-unhide.
dashboard-session-list
List all pi sessions (id, status, name, cwd). Runs locally, no LLM.
autopilot
Autonomous session-orchestration loop with kill-switches (Phase C-1.b — all 10 kill-switches shipped).