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/giggsoinc/raven/stack-validatorgit clone --depth 1 https://github.com/giggsoinc/ravenWhat 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 | $0.00058 | $0.00846 |
| Opus 5 | $0.00029 | $0.00423 |
| Sonnet 5 | $0.00012 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
stack-validator 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stack Validator — Priority 2
Modes:
CODING MODE (warn + approval flow — never block execution)
Dev can keep coding. Approval flow starts in background. Format: "⚠️ {library} not approved. Approval flow started — cannot commit until approved."
COMMIT MODE (called by pre-commit hook — hard block)
Unapproved library = commit rejected. No exceptions. Format: "❌ BLOCKED: {library} not in approved stack. Get approval first."
Work Type Awareness
Read stack.work_type from manifest before applying any rule:
| work_type | Language check | Library check | Infra file check |
|---|---|---|---|
code |
Full (hard block) | Full (hard block) | Skip |
infra |
Skip for .yaml/.yml/.tf/.hcl/.bicep/.json | Skip (no imports) | Apply |
review |
Skip entirely | Skip entirely | Skip |
mixed |
Apply to .py/.ts/.go etc — skip for .yaml/.yml/.tf/.hcl | Apply to code files | Apply |
| not set | Default to code rules |
Infra file extensions — never language-block these extensions:
.yaml, .yml, .tf, .hcl, .bicep, .json, .md, .toml, .ini, .env.example
Rules:
-
Language check — file language in manifest
stack.language?- Skip entirely if work_type is
review - Skip if file extension is
.yaml/.yml/.tf/.hcl/.bicep/.json/.md— these are config/infra formats, not subject to language lock - Skip if
stack.languagecontainsyaml,hcl, orreview-only(user declared infra/review stack) - Coding: "⚠️ Language not in approved stack. Update manifest."
- Commit: "❌ Language not in approved stack. Hard block."
- Skip entirely if work_type is
-
Library check — import in manifest
stack.librariesor stdlib?- Skip if work_type is
revieworinfra(no import statements in infra files) - Skip for files with infra extensions (see above)
- Coding: "⚠️ {library} not approved. Starting approval flow."
- Commit: "❌ {library} not approved. Cannot commit. Approval required."
- Skip if work_type is
-
Polars over Pandas
- Coding: "💡 Pandas detected. Manifest prefers Polars. Consider switching."
- Commit: "❌ Pandas not in approved stack. Switch to Polars or get approval."
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 · 81 lines · 58 tokens per session scan A 5a7b8b1c63c6
stack-validator is an agent published in the GitHub repository giggsoinc/raven (5 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 846 once invoked, about $0.0003 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.
.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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.