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 nullproof-studio/en-quire --skill en-quiregit clone --depth 1 https://github.com/nullproof-studio/en-quireWrote 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/nullproof-studio/en-quire/en-quire)<a href="https://agentmods.dev/skills/nullproof-studio/en-quire/en-quire"><img src="https://agentmods.dev/badge/skills/nullproof-studio/en-quire/en-quire/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/nullproof-studio/en-quire/en-quire"><img src="https://agentmods.dev/badge/skills/nullproof-studio/en-quire/en-quire.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 | $0.00159 | $0.07901 |
| Opus 5.5 | $0.00064 | $0.03160 |
| Sonnet 5.5 | $0.00032 | $0.01580 |
| Haiku 4.5 | $0.00016 | $0.00790 |
Grade A, and why
en-quire 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 — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: en-quire — Markdown Document Management
Purpose: Instructions for agents using en-quire MCP tools to read, search, edit, and manage markdown and YAML documents.
Orientation: Multi-Root and doc_status
en-quire manages documents across multiple roots — separate directories for different document types (e.g. codex, agents, skills, testing). Each root can have its own git configuration and governance model.
Start every session with:
doc_status— see all configured roots, their git status, index health, and pending proposalsdoc_list— see all files, or scope to a specific root withdoc_list(scope: "skills")
File paths include the root prefix: codex/en-quire.mdx, agents/researcher.md, skills/en-quire/SKILL.md. Use the prefix in all tool calls — or, if you already hold a filesystem path from another tool, pass the absolute path as-is: it resolves to the root that contains it. The same goes for scope (e.g. an absolute directory in doc_list or doc_search). Absolute paths outside every configured root are rejected. Responses always use the root-prefixed form.
Search works across all roots by default. Scope to a single root with doc_search(query: "...", scope: "agents").
When to Use en-quire
For files inside a configured root, use en-quire tools (doc_*) instead of your client's filesystem tools (in Claude Code: Read, Edit, Write; on an MCP filesystem server: read_text_file, edit_file, write_file) for any operation on:
- Markdown files (.md, .mdx) — SOPs, skill files, codex articles, session memory, agent profiles
- YAML files (.yaml, .yml) — Docker Compose, config files, CI/CD pipelines, Kubernetes manifests
en-quire provides section-level addressing, structural search, and diff responses that eliminate the need to read or rewrite whole files. For YAML, "sections" are key paths (e.g. services.api.environment).
Use filesystem tools only when:
- The file is outside every configured root (check
doc_statusif unsure). en-quire rejects those paths, so don't retry them throughdoc_*. - You are working with file types en-quire doesn't support (JSON, JS, etc.)
- You need to move or copy files between directories or roots
What ships with it
3 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 Changed · +60 lines · +44 tokens per session 35f0184e130e
- 8d ago Changed · +38 lines e315919e5c0c
- 1mo ago First seen · 376 lines · 115 tokens per session scan A 5782d552fd3c
en-quire is a skill published in the GitHub repository nullproof-studio/en-quire (0 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 7,901 once invoked, about $0.0006 per session on Opus 5.5. 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
markdown-documents
Write or edit Markdown notes, reports and plain text; default for non-Office writing.
siemens-tia-portal-integrator
Orchestrate data-driven Siemens TIA Portal workflows: read structured data from CSV/Excel files, generate STL/AWL code via the siemens-awl-stl-programmer skill, and apply changes to a live TIA Portal project. Trigger when the user asks to import, generate, sync, or batch-apply PLC blocks, tags, devices, or data blocks…
anywrite
Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.
deep-search
A research and document-writing workflow that searches multiple sources, including Bilibili, the web, and a knowledge base, then creates documents. It supports Word, PowerPoint, Excel, and PDF output.
content-creation
A Chinese-language content-creation skill covering images, documents, presentations, videos, speech, music, and finding inspiration on Bilibili, a Chinese video-sharing platform.
paperless-todo-cleanup
Process Paperless-ngx documents tagged "TODO" — pick a meaningful title, set correspondent/documenttype/created where determinable, and apply 3-4 tags (reusing existing ones), then clear the TODO tag. Use when the user asks to work through TODO-tagged documents, clean up the Paperless inbox, or process…