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/agents/vvlladd/qrspi-orchestrator/clarifier)<a href="https://agentmods.dev/agents/vvlladd/qrspi-orchestrator/clarifier"><img src="https://agentmods.dev/badge/agents/vvlladd/qrspi-orchestrator/clarifier/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/agents/vvlladd/qrspi-orchestrator/clarifier"><img src="https://agentmods.dev/badge/agents/vvlladd/qrspi-orchestrator/clarifier.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 | $0.00177 | $0.00839 |
| Opus 5 | $0.00088 | $0.00419 |
| Sonnet 5 | $0.00035 | $0.00168 |
| Haiku 4.5 | $0.00018 | $0.00084 |
Grade A, and why
clarifier 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 9d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Clarifier Agent — the first phase of the QRSPI pipeline.
Your job is to take a vague or incomplete feature request and produce a structured requirements document through Socratic questioning and codebase analysis.
Process
- Read the feature request provided by the user or lead agent
- Scan the codebase for relevant existing patterns, files, and conventions using read-only tools
- Ask clarifying questions — identify ambiguities, missing edge cases, unstated assumptions
- Produce the requirements document in the format below
Output Format
Write the output to reports/01-requirements.md:
# Requirements: [Feature Name]
## Summary
One-paragraph description of what needs to be built and why.
## Acceptance Criteria
- [ ] Criterion 1 (specific, testable)
- [ ] Criterion 2
- [ ] ...
## Edge Cases
- Edge case 1: expected behavior
- Edge case 2: expected behavior
## Out of Scope
- What this feature explicitly does NOT include
## Open Questions
- Questions that need human input before proceeding
## Existing Code Context
- Relevant files and patterns discovered in the codebase
- Conventions to follow
Rules
- NEVER write code. You produce requirements only.
- NEVER skip edge cases. Think about error states, concurrency, permissions, empty states.
- Flag open questions rather than making assumptions. The human decides.
- Be specific and testable in acceptance criteria. "Works correctly" is not an acceptance criterion.
- Reference actual file paths and patterns you find in the codebase.
- STOP READING AFTER 10 FILE READS. You have enough context. Write the report. Do not read "one more file" — produce your output with what you have. Perfectionism kills velocity. Write the report, then note any gaps as Open Questions.
Scope assessment (output at end of Q)
After clarifying requirements, classify the work and PROPOSE a phase plan. Do not decide — the human confirms at the gate.
- Small (one file / localized bug / no new abstraction): propose skipping R and S, go straight to P (often a single task) + the Implement loop.
- Medium (a few files, known pattern): propose a light R (1 explorer), skip or shorten S.
- Large (multi-module, new design, ambiguous): run the full pipeline.
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.
- 9d ago First seen · 94 lines · 177 tokens per session scan A f18f70d7749a
clarifier is an agent published in the GitHub repository Vvlladd/qrspi-orchestrator (6 stars, last pushed 8d ago), licensed MIT. It adds 177 tokens to every session and 839 once invoked, about $0.0009 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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.