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/Vvlladd/qrspi-orchestratorWrote 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/vvlladd/qrspi-orchestrator/qrspi)<a href="https://agentmods.dev/commands/vvlladd/qrspi-orchestrator/qrspi"><img src="https://agentmods.dev/badge/commands/vvlladd/qrspi-orchestrator/qrspi/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/vvlladd/qrspi-orchestrator/qrspi"><img src="https://agentmods.dev/badge/commands/vvlladd/qrspi-orchestrator/qrspi.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 | $0.00010 | $0.00918 |
| Opus 5 | $0.00005 | $0.00459 |
| Sonnet 5 | $0.00002 | $0.00184 |
| Haiku 4.5 | $0.00001 | $0.00092 |
Grade A, and why
qrspi 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QRSPI Pipeline Orchestrator
You are starting the QRSPI multi-agent pipeline. This is the main entry point.
Setup
-
Create the working directories if they don't exist:
mkdir -p reports/ -
Initialize
progress.mdif it doesn't exist:# QRSPI Progress Log Feature: $ARGUMENTS Started: [current timestamp] -
Initialize
tasks.jsonas empty if it doesn't exist.
Pipeline Execution
Execute each phase in order. STOP after each phase and wait for human approval before proceeding.
Phase 1: Questions
Delegate to the clarifier agent with the feature description: $ARGUMENTS
After the clarifier produces reports/01-requirements.md, present a summary to the human and ask:
- "Requirements are ready. Review reports/01-requirements.md and let me know: approve, request changes, or reject."
DO NOT proceed to Phase 2 until the human explicitly approves.
Phase 2: Research (Agent Team)
Create an agent team with 2-3 explorer teammates, each assigned a different area:
- Explorer 1: Core feature area (the primary files and modules)
- Explorer 2: Adjacent systems (dependencies, integrations, APIs)
- Explorer 3: Tests and infrastructure (existing test patterns, CI, configs)
Have the explorers share findings with each other. The lead synthesizes into reports/02-exploration.md.
Present summary and ask for approval before proceeding.
Phase 3: Design (Agent Team)
Create an agent team with 3 teammates:
- Architect: Produces the design document
- Critic: Challenges every design decision, proposes alternatives
- Security Reviewer: Audits for security implications
Require plan approval from the architect before they write. The critic and security reviewer message the architect with feedback. The architect revises until the team converges.
The lead writes the final reports/03-design.md.
Present summary and ask for approval before proceeding.
Phase 4: Plan
Delegate to the planner agent to decompose the design into tasks.
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 · 104 lines · 10 tokens per session scan A ab5067f97e5a
qrspi is a command published in the GitHub repository Vvlladd/qrspi-orchestrator (6 stars, last pushed 12d ago), licensed MIT. It adds 10 tokens to every session and 918 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 commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.