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/auditnpx skills add rodlunt/engineering-audit --skill auditgit 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 | $0.00057 | $0.00965 |
| Opus 5 | $0.00028 | $0.00483 |
| Sonnet 5 | $0.00011 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
audit scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
server with `curl`, and do not try to open the browser yourself. Calling `get_config` while its How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering practice audit
Runs a full engineering-practice audit of the current repository via the engineering-audit
MCP server, and produces a self-contained HTML report.
The full, assistant-neutral procedure lives in this tool's own AUDIT.md (in the
engineering-audit repository this server was installed from). Follow that document as the
source of truth. The summary below exists so you do not have to fetch it before starting, but
if the two ever disagree, AUDIT.md wins.
Flow (summary)
- Gather run metadata: repository name,
git rev-parse HEAD, your own assistant/model identity, an ISO 8601 started timestamp, and the host environment (see below). - Call
begin_runwith that metadata andoutput_dirset to<repo>/audit-output/. Passenvironmentwith exactly these keys, omitting any you cannot determine:os(read from the machine, e.g.uname -srorsw_vers),host_cli("claude-code") andhost_cli_version(claude --version). Any other key is refused: seeAUDIT.mdstep 1 for why the set is closed. - Call
start_config.- Preset mode (
ENGINEERING_AUDIT_CONFIGenv var set): the config is already loaded, skip to step 4. - Interactive mode: the response has a
url. Show it to the user as a clickable line (do not open it yourself, and do not try to fetch or wait on it via Bash) and ask them to choose domains there. Then callget_configin a loop: while its response'sstatusis"waiting", call it again. Go to step 4 only once the status is"configured". - If
get_configraises, the run's overall waiting deadline has expired. Tell the user plainly that the audit is waiting on them and stop. Do not proceed with a guessed domain selection. Callget_configagain, with a largertimeout_s, once they confirm.
- Preset mode (
- For each selected domain id: call
get_domain, read the full rule text, sweep the repository giving every rule an honest verdict (pass,finding, ornot-applicableorcould-not-evaluatewith a reason: never a guessedpass), then callrecord_domain_result. If it rejects the payload as incomplete, the error lists the missing rule ids; fix and resubmit. Write every finding and issue body terse, in three parts and nothing else: the issue, why it matters, suggested fix (one or two sentences each). - Call
run_statusand confirm nothing is missing. - Call
render_reportwith a finished timestamp. Tell the user wherereport.htmllanded and give a one-line findings summary.
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 · 60 lines · 57 tokens per session scan A 7e51202a8c06
audit is a skill published in the GitHub repository rodlunt/engineering-audit (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 57 tokens to every session and 965 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…