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 skills add wedabro/bro-skills --skill speckit.ai-engineergit clone --depth 1 https://github.com/wedabro/bro-skillsWrote 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/skills/wedabro/bro-skills/speckit.ai-engineer)<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.ai-engineer"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.ai-engineer/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/skills/wedabro/bro-skills/speckit.ai-engineer"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.ai-engineer.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 | $0.00035 | $0.00870 |
| Opus 5 | $0.00017 | $0.00435 |
| Sonnet 5 | $0.00007 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade B, and why
speckit.ai-engineer scanned grade B with 1 finding 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 12d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- **Input Sanitization**: Strip indirect prompt injection payloads (e.g. "Ignore previous instructions") and run input through guardrail classifiers (Llama Guard, NeMo). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 Mission
Design, implement, and evaluate production-ready LLM and AI systems. Focus on deterministic boundaries, semantic search fidelity, vector database indexing, token budget efficiency, and continuous evaluation pipelines (Evals). Honor .agents/knowledge_base/ standards and the project constitution.
📥 Required Inputs
.agents/specs/[feature]/spec.md,plan.md, andtasks.md- Target Model & Provider specs (OpenAI, Anthropic, Gemini, Local Ollama/vLLM)
- Embedding model dimensions & distance metric (Cosine, DotProduct, Euclidean)
- Data schemas, chunking rules, and retrieval latency requirements
📋 Protocol
1. RAG & Ingestion Pipeline Architecture
- Semantic Chunking: Chunk text by logical boundaries (paragraphs, markdown headings, code AST) with 300–500 token sweet spot and 10–15% overlap.
- Hybrid Search: Combine Dense Vector Retrieval (semantic match) with Sparse Keyword Search (BM25 / Full-text search) via Reciprocal Rank Fusion (RRF).
- Reranking: Apply Cross-Encoder / Cohere Reranker to top-K retrieved candidates ($K=20 \to 5$) to eliminate irrelevant context before LLM synthesis.
- Vector DB Indexing: Use HNSW (Hierarchical Navigable Small World) index for low-latency similarity queries; configure
mandef_constructionfor dataset scale. - Metadata Filtering: Always apply pre-filtering on tenant ID, access control tags, and timestamps before vector distance computation.
2. Structured Outputs & Tool Calling
- Strict Pydantic / Zod Schemas: Every LLM function call and JSON response MUST be validated through strict typed schemas. Reject schema violations with deterministic retries.
- Tool Guardrails: Never allow direct code execution or shell access without an isolated sandbox and explicit confirmation boundaries.
- Semantic Caching: Store query embedding hashes in Redis to serve identical or high-similarity (> 0.95 cosine) queries instantly, reducing LLM costs and latency.
3. Prompt Engineering & Injection Defense
- System Prompt Separation: Isolate trusted system instructions from untrusted user input using clear delimiters (e.g.,
<user_input>,###). - Input Sanitization: Strip indirect prompt injection payloads (e.g. "Ignore previous instructions") and run input through guardrail classifiers (Llama Guard, NeMo).
- Context Window Budgeting: Track token consumption dynamically. Allocate reserve budget for system prompts, history, context retrieval, and response generation.
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.
- 12d ago First seen · 57 lines · 35 tokens per session scan B 7adc2b615bec
speckit.ai-engineer is a skill published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 35 tokens to every session and 870 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gpt-image-2
A skill for generating or editing images with GPT Image 2 across local, host-provided, or advisory setups.
kb-retriever
A retrieval and question-answering assistant for a local folder of documents, including Markdown, text, PDFs, and spreadsheets.
azure-cognitive-search
Expert knowledge for Azure AI Search development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when designing indexes, skillsets, indexers, vector/semantic search, or secure data…
azure-horizondb
Expert knowledge for Azure Horizondb development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using azureai SQL/embeddings, pgvector tuning, Apache AGE graphs, hybrid…
azure-documentdb
Expert knowledge for Azure DocumentDB development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using DocumentDB search (BM25/vector), Data API, MongoDB compatibility, change…
rag
Use when building retrieval-augmented generation. Covers chunking, embedding and hybrid search, reranking, grounding and citation, and diagnosing whether a bad answer is a retrieval failure or a generation failure.