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 skills/rodlunt/engineering-audit/engineering-grillnpx skills add rodlunt/engineering-audit --skill engineering-grillgit clone --depth 1 https://github.com/rodlunt/engineering-auditWhat 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 | $0.00078 | $0.05011 |
| Opus 5 | $0.00039 | $0.02506 |
| Sonnet 5 | $0.00016 | $0.01002 |
| Haiku 4.5 | $0.00008 | $0.00501 |
Grade A, and why
engineering-grill 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Grill
Begin only when the user explicitly invokes Engineering Grill.
Run a structured project-start interview grounded in the engineering framework. Reach a shared understanding of what must be designed, built, and verified. Leave project implementation for a separate request after the interview.
Treat the framework as decision support. The intended system determines applicability. An empty or new repository is evidence about project stage, not evidence that a domain is irrelevant.
Say this once, early, in your own words. This flow has never been run end to end with a real person answering. Question derivation has been exercised against a single brief on a few domains; the cross-domain triage and the deep dive have not been run at all. The user should know that before they invest an hour in it, and should be asked to report anything that reads like a generic quiz rather than a question about their actual work, because that is the failure mode this design is most likely to have.
Two modes, and the difference is only what evidence you start from. before questions intent
when no plan exists, and is the primary mode. review questions a drafted plan, naming the
decisions it made silently or did not make at all. Take the mode from the invocation if given.
With no argument, pick the obvious one (a plan file with real content in it means review) and
confirm in one question. Never assume silently.
Load the live framework
Use the engineering-audit MCP's read-only tools as the canonical source:
- Call
list_domainsat the start of every session. Check the returned domain triggers, rule counts, andskipped_files. State how many domains were loaded. Report skipped files because they make the visible coverage incomplete. - Call
get_domain("dNN")when a domain becomesactive-now. Read the full returned document before deriving questions from it. - Use only
list_domainsandget_domain. Never callbegin_run,record_domain_result,file_issuesorrender_report. Those belong to theauditskill. They demand a repository name and a commit, and work that has not started yet has neither. This interview is not an audit run and produces no audit verdict or report.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 396 lines · 78 tokens per session scan A 429597cc5607
engineering-grill is a skill published in the GitHub repository rodlunt/engineering-audit (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 78 tokens to every session and 5,011 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 2026-08-31.
Other skills, from other repositories
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
unity-vrc-world-sdk-3
VRChat World SDK 3 guide for scene and Inspector setup, component placement, optimization, and upload. Use for VRChat world scene configuration, VRC SDK components, layers, baked lighting, Quest/Android performance, Dynamics for Worlds, Build Panel warning triage, validation, and upload. Covers VRCSceneDescriptor…
unity-vrc-skills-renovator
VRChat skill renovator for knowledge fill, refresh, and quality improvement. Use this skill when updating VRChat skills to new SDK versions, filling missing knowledge, fixing outdated information, or improving skill quality. Targets unity-vrc-udon-sharp and unity-vrc-world-sdk-3 skills. Triggers on: update skills, SDK…
neo4j-cypher-skill
Generates, optimizes, and validates Cypher 25 queries for Neo4j 2025.x and 2026.x. Use when writing new Cypher queries, optimizing slow queries, graph pattern matching, vector or fulltext search, subqueries, or batch writes. Covers MATCH, MERGE, CREATE, WITH, RETURN, CALL, UNWIND, FOREACH, LOAD CSV, SEARCH…