MCPGateway: Skill for Claude Code

.agents/skills/doc-coauthoring/SKILL.md

doc-coauthoring is a skill for Claude Code from abdullah1854/MCPGateway. It costs 47 tokens per session (1,238 once invoked), scanned A, original, MIT.

A guided workflow for collaboratively writing documents such as proposals, specifications, design documents, and user guides.

In plain words
What is it for?
It is for gathering requirements, exploring options, drafting sections, asking focused questions, and refining the document with feedback.
Why use it?
It helps turn scattered context and feedback into a document whose audience, purpose, decisions, and constraints are clear.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; installed under .agents/ (shared by several agents).

This is abdullah1854/MCPGateway's own configuration. It tells Claude Code how to work on MCPGateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MCPGateway configures →

Reuse

Borrowing it

Nothing to install: this file belongs to abdullah1854/MCPGateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/abdullah1854/MCPGateway/main/.agents/skills/doc-coauthoring/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/abdullah1854/MCPGateway

Made for: Claude Code.

Wrote 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.

agentmods badge for doc-coauthoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/doc-coauthoring/github.svg)](https://agentmods.dev/skills/abdullah1854/mcpgateway/doc-coauthoring)
Your own site
<a href="https://agentmods.dev/skills/abdullah1854/mcpgateway/doc-coauthoring"><img src="https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/doc-coauthoring/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.

agentmods 80×15 button for doc-coauthoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/abdullah1854/mcpgateway/doc-coauthoring"><img src="https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/doc-coauthoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,238 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.01238
Opus 5 $0.00023 $0.00619
Sonnet 5 $0.00009 $0.00248
Haiku 4.5 $0.00005 $0.00124

Measured 9d ago against content hash 9387a60ceb64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

doc-coauthoring 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 9d 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.

.agents/skills/doc-coauthoring/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document Co-Authoring Skill

When This Skill Activates

  • "Write a document", "draft a proposal"
  • "Create a spec", "design document"
  • "Help me write", "co-author"
  • "RFC", "ADR", "technical spec"
  • "Documentation", "user guide"

Three-Stage Workflow

Stage 1: Context Gathering

Start with meta-context questions:

  1. Who is the audience?
  2. What's the purpose/goal?
  3. What decisions need to be made?
  4. What constraints exist?
  5. What's the deadline/urgency?

Then info dump:

  • Ask user to share all relevant context
  • Notes, prior docs, requirements
  • Stakeholder preferences
  • Examples of similar docs they like

Clarifying questions:

  • Ask 3-5 targeted questions
  • Ensure understanding before drafting
  • Surface hidden assumptions

Stage 2: Section-by-Section Drafting

For each section:

1. ASK clarifying questions for this section
2. BRAINSTORM 5-20 options/approaches
3. CURATE down to best options
4. DRAFT the section
5. REFINE based on feedback

Feedback guidance:

  • "Specific feedback helps!" not just "looks good"
  • "What's missing?" "What's confusing?"
  • "What would [stakeholder] push back on?"

Surgical edits:

  • Never reprint entire sections
  • Use targeted replacements
  • Preserve voice and flow

Stage 3: Reader Testing

Fresh perspective test:

  1. Imagine a reader with NO context
  2. Can they answer key questions?
  3. Are there gaps or ambiguities?
  4. What questions would they ask?

Predicted questions:

Q: What problem does this solve?
A: [Answer from doc - check clarity]

Q: Why this approach vs alternatives?
A: [Answer from doc - check completeness]

Q: What are the risks?
A: [Answer from doc - check thoroughness]

Document Templates

Technical Spec / RFC

# [Feature Name] - Technical Specification

## Status
Draft | Review | Approved | Implemented

## Summary
[1-2 sentence overview]

## Background
[Context and problem statement]

## Goals
- [Goal 1]
- [Goal 2]

## Non-Goals
- [What this does NOT address]

## Proposed Solution
[Detailed description]

### Architecture
[Diagrams, components, data flow]

### API Changes
[Endpoints, schemas, breaking changes]

## Alternatives Considered
### Option A: [Name]
- Pros: [...]
- Cons: [...]

### Option B: [Name]
- Pros: [...]
- Cons: [...]

## Security Considerations
[Auth, data protection, attack vectors]

## Testing Plan
[How to verify correctness]

## Rollout Plan
[Phased rollout, feature flags, rollback]

## Open Questions
- [ ] [Question 1]
- [ ] [Question 2]

Read the full file on GitHub · 255 lines

Changes

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.

  1. 9d ago First seen · 255 lines · 47 tokens per session scan A 9387a60ceb64

Subscribe to this mod's changes

doc-coauthoring is a skill published in the GitHub repository abdullah1854/MCPGateway (15 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,238 once invoked, about $0.0002 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 2026-08-30.