Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vanessamarely/ai-playbook-repositonpx agentmods add agents/vanessamarely/ai-playbook-reposito/scan-workspaceWrote 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/vanessamarely/ai-playbook-reposito/scan-workspace)<a href="https://agentmods.dev/agents/vanessamarely/ai-playbook-reposito/scan-workspace"><img src="https://agentmods.dev/badge/agents/vanessamarely/ai-playbook-reposito/scan-workspace/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/vanessamarely/ai-playbook-reposito/scan-workspace"><img src="https://agentmods.dev/badge/agents/vanessamarely/ai-playbook-reposito/scan-workspace.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 | $0.00021 | $0.00975 |
| Opus 5 | $0.00010 | $0.00487 |
| Sonnet 5 | $0.00004 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
scan-workspace 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 10d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Workspace Agent
Purpose
Identify the project type within a target folder, determine which skills apply, and verify that AI tool instruction files (GitHub Copilot, Claude Code, Cursor, Codex CLI) are present and up to date.
Inputs
targetFolder: Absolute or relative path to the project root.
Outputs
- JSON structure containing:
projectType: Detected type (e.g.,react,node-service,java-spring,python-fastapi).skills: List of applicable skill identifiers.aiTools: Status of AI instruction files present in the project.warnings: Any issues detected (missing dependencies, inconsistent configuration, missing AI tool files).
Procedure
Step 1: Validate Target Folder
- Verify the folder exists.
- Check read permissions.
- If validation fails, output error and exit.
Step 2: Run Project Detection
Execute: node tools/project-detect.mjs <targetFolder>
Expected output: JSON with project metadata.
If the script fails:
- Check that Node.js is available.
- Verify the script path is correct relative to the playbook root.
- Output the stderr and exit.
Step 3: Parse Detection Results
Extract:
projectTypeframework(if applicable)language- Configuration file paths
Step 4: Map to Skills
Use the following routing table:
| Project Type | Skills |
|---|---|
react |
react-components, a11y-automation |
node-typescript |
node-typescript-service |
java-spring |
(Refer to backend-policy.md; no specific skill yet) |
python-fastapi |
(Refer to backend-policy.md; no specific skill yet) |
unknown |
Fallback to manual inspection |
Step 5: Check AI Tool Instruction Files
For each AI tool, verify the instruction file exists in targetFolder:
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.
- 10d ago First seen · 127 lines · 21 tokens per session scan A b174643596c3
scan-workspace is an agent published in the GitHub repository vanessamarely/ai-playbook-reposito (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 975 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.
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.