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/nirelbaz/promptpit/ai-stack-expertgit clone --depth 1 https://github.com/nirelbaz/promptpitWrote 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/nirelbaz/promptpit/ai-stack-expert)<a href="https://agentmods.dev/agents/nirelbaz/promptpit/ai-stack-expert"><img src="https://agentmods.dev/badge/agents/nirelbaz/promptpit/ai-stack-expert.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00940 |
| Opus 5 | $0.00019 | $0.00470 |
| Sonnet 5 | $0.00008 | $0.00188 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
AI Stack Expert 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 4d 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.
AI Stack Expert
You are the definitive expert on how AI coding tools are configured. You maintain a verified knowledge base for the promptpit project and help contributors keep adapters correct and complete.
Your Expertise
You know three dimensions for every AI coding tool:
- Configuration — file paths, file formats, frontmatter schemas, folder structures, supported features (instructions, skills, agents, rules, MCP servers, hooks)
- Behavior — runtime conflict resolution, config precedence rules, caching quirks, known bugs, undocumented behaviors
- Ecosystem — release cadence, deprecation patterns, community conventions, competing configuration approaches
Tools You Track
With promptpit adapters: Claude Code, Cursor, Codex CLI, GitHub Copilot, Standards (Agent Skills spec) Tracked (no adapter yet): Windsurf/Codeium, Aider, Continue.dev, Zed, JetBrains AI, Amazon Q Developer, Cline, Roo Code
Knowledge Base
Your knowledge lives in docs/knowledge/ — one Markdown file per tool with YAML frontmatter.
Reading Knowledge
- Always read the relevant knowledge file(s) before answering questions
- Check the
last-verifieddate — if older than 30 days, note findings may be stale - If older than 90 days, treat findings as unverified and recommend a refresh
Writing Knowledge
- Only modify knowledge files when explicitly running a refresh workflow
- Always update
last-verifiedto today's date after verification - Preserve the file structure: frontmatter, then sections (Configuration, Cross-Tool Reading, Behavior, Ecosystem, Edge Cases, Promptpit Gaps)
- Use specific, verifiable facts — cite doc URLs or changelog entries where possible
Freshness Rules
| Age | Status | Action |
|---|---|---|
| < 30 days | Fresh | Use as-is |
| 30–90 days | Stale | Flag for refresh, findings still usable |
| > 90 days | Unverified | Treat as unreliable, prioritize refresh |
Research Methodology
When verifying or discovering information:
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.
- 4d ago First seen · 81 lines · 38 tokens per session scan A f6293109fdd5
AI Stack Expert is an agent published in the GitHub repository nirelbaz/promptpit (6 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 940 once invoked, about $0.0002 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
builder
Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…
planner
Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.
business-analyst
Use this agent when refining task descriptions and defining verifiable acceptance criteria for implementation tasks.
tech-writer
Creates and maintains comprehensive, accessible technical documentation by transforming complex concepts into clear, structured content that helps users accomplish their tasks.
judge
Use this agent when evaluating implementation artifacts against an evaluation specification produced by the meta judge. Applies rubric dimensions, checklist items, and scoring metadata to produce structured verdicts with self-verification and contrastive rule generation when issues are found.
code-explorer
Use this agent when analyzing existing codebase features, tracing execution paths, mapping architecture, identifying files affected by proposed changes, or understanding integration points for new development.