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/microsoft/p.808/create-studygit clone --depth 1 https://github.com/microsoft/P.808What 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 | $0.00079 | $0.10194 |
| Opus 5 | $0.00039 | $0.05097 |
| Sonnet 5 | $0.00016 | $0.02039 |
| Haiku 4.5 | $0.00008 | $0.01019 |
Grade A, and why
create-study 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 2d 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 — 850 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create subjective test instructions
Use this runbook when asked to create a new subjective speech quality test with the P.808 toolkit.
Trigger phrases: "create a study", "run a [method] test", "set up a [method] study", "prepare a [method] test for these files".
Platform and shell adaptation
Code examples use PowerShell on Windows (\ paths). Adapt for other OS/shells:
replace PowerShell cmdlets with equivalents, use python3 if needed, convert paths.
Replace REPO_ROOT with the actual absolute path of this repository.
Best-practice variables
These are best-practice defaults. Confirm or override them with the requester before first use.
After confirmation, save a .cfg file next to the input files so future runs can reuse it.
When asked to re-run a test or "go yolo", look for an existing config file first.
BEST_PRACTICE_PLATFORM = Prolific
BEST_PRACTICE_VALID_VOTE_BUFFER = 20%
BEST_PRACTICE_CLIPS_PER_SESSION = 10
BEST_PRACTICE_GOLD_PER_SESSION = 1 (use 2 for P.804 — see method-specific notes)
BEST_PRACTICE_TRAPPING_PER_SESSION = 1
BEST_PRACTICE_TRAINING_CLIPS = 5
BEST_PRACTICE_GOLD_SOURCE_COUNT = max(3, ceil(0.05 * number_of_rating_clips))
BEST_PRACTICE_TRAPPING_SOURCE_COUNT= max(3, ceil(0.05 * number_of_rating_clips))
BEST_PRACTICE_MAX_GOLD_SOURCE_CLIPS = 15
BEST_PRACTICE_MAX_TRAPPING_SOURCE_CLIPS= 15
BEST_PRACTICE_ALLOWED_MAX_HITS = min(int(number_of_rating_clips / 10), 50)
BEST_PRACTICE_BASE_PAYMENT = 0.50
BEST_PRACTICE_QUANTITY_BONUS = 0.10
BEST_PRACTICE_QUALITY_BONUS = 0.15
BEST_PRACTICE_BW_MIN = FB
Scope
This instruction covers preparing inputs, generating gold/trapping clips, uploading to
storage, running master_script.py, and handing off for publishing. Setting up the HIT
in a HITAPP server and publishing is done by the requester.
Mandatory pre-check
Before editing or running anything in this repository:
- Read
AGENTS.mdand.github\copilot-instructions.md. - Confirm this is a creation task, not analysis. For analysis, use
.github\evaluate.instruction.mdinstead.
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.
- 2d ago First seen · 850 lines · 79 tokens per session scan A 4ce693e1f0ee
create-study is an agent published in the GitHub repository microsoft/P.808 (230 stars, last pushed 14d ago), licensed MIT. It adds 79 tokens to every session and 10,194 once invoked, about $0.0004 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 2026-08-30.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.