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 LuuOW/meridian-mcp --skill internal-docs-operatorgit clone --depth 1 https://github.com/LuuOW/meridian-mcpWrote 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/luuow/meridian-mcp/internal-docs-operator)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/internal-docs-operator"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/internal-docs-operator.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 5.1 | $0.00046 | $0.01100 |
| Opus 5 | $0.00023 | $0.00550 |
| Sonnet 5 | $0.00009 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
internal-docs-operator 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 7d 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.
curl -s http://45.9.190.170:4401/ | grep -n "target-id" How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
internal-docs-operator
Workflow for operating on the internal docs system without drifting to the wrong target or claiming unverified success.
1) Source Hierarchy
Treat the two internal surfaces differently:
http://45.9.190.170:4400or localhttp://127.0.0.1:4400Higher-authority live operational source for system state, services, PM2, Docker, ports, uptime, and environment facts.http://45.9.190.170:4401Curated internal reference layer for topology, project descriptions, onboarding, and conventions.
Do not treat :4401 as unconditional truth. Use it for orientation, then verify live operational claims against :4400, direct commands, or source files.
2) Exact Target Discipline
If the user gives any explicit target, treat it as mandatory:
- URL
- hash like
#card-openclaw-workspace-3 - project/card/panel id
- path
- port
Do not silently switch to another card, panel, section, or project because it is visible by default.
Before acting, resolve:
- what the requested target is
- where the backing content actually lives
- whether the task is editing:
- a source file
- a generated template
- a backing API
- a runtime-rendered UI only
3) Required Execution Sequence
For any docs-site modification:
- Inspect the requested target
- Identify the real storage layer
- Make the edit at the source, not by scraping UI
- Restart/reload the serving process if required
- Verify the exact target changed
- Only then report success
If step 2 is unresolved, do not proceed as if the update path is known.
4) Observed vs Inferred vs Verified
Always keep these separate:
observedDirectly seen in source, command output, or live pageinferredLikely true from structure, but not yet provenverifiedConfirmed on the exact requested target after the action
Do not write “done”, “updated”, “added”, or “success” unless the requested effect is verified.
5) Working With :4401
When using the docs site:
- inspect the actual source file if the app is file-backed
- prefer source edits over brittle DOM injection or shell regex surgery
- if the app is served from a single template file, edit that source directly
- verify the relevant section, panel, card, or anchor after reload
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.
- 7d ago First seen · 143 lines · 46 tokens per session scan A 6a14b73f541f
internal-docs-operator is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 1,100 once invoked, about $0.0002 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
docs-page
A long-form technical documentation page with a left navigation panel, a main article, and a right table of contents. A table of contents lists the page sections and links to them.
librechat-docs
Use the official LibreChat documentation to install, configure, operate, and troubleshoot LibreChat.
documentation-authoring
Create structured docs from scratch — PRDs, technical specs, design docs, decision records, knowledge bases. Use when drafting documentation, writing proposals, defining requirements, or planning features.
documentation-patterns
Templates and structural patterns for API docs, feature docs, config guides, and REST endpoint documentation. Use when structuring docs, applying Markdown templates, or standardizing doc formats.
documentation-quality
Documentation quality standards and writing principles. Use when establishing formatting rules, reviewing doc quality metrics, creating writing guidelines, or enforcing consistent documentation style across a project.
documentation-automation
Automate doc generation with JSDoc/TSDoc, linters, and pre-commit hooks. Use when setting up markdownlint, configuring doc linting pipelines, integrating JSDoc/TSDoc, or building automated documentation workflows.