pattern-mcp: Skill for Claude Code

.claude/skills/pattern-docs-sync/SKILL.md

pattern-docs-sync is a skill for Claude Code from donaldrichard19-LVD/pattern-mcp. It costs 76 tokens per session (1,183 once invoked), scanned A, original, MIT.

A documentation workflow for keeping two published project documents aligned with the repository's backlog and shipped architecture changes.

In plain words
What is it for?
Use it when adding backlog sections or confirming architecture changes that have shipped, so the matching briefing and engineering primer stay current.
Why use it?
It prevents public documentation from becoming outdated or disconnected from the codebase. It also reduces the risk of overwriting newer edits when updating the documents.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is donaldrichard19-LVD/pattern-mcp's own configuration. It tells Claude Code how to work on pattern-mcp 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 pattern-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to donaldrichard19-LVD/pattern-mcp. 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/donaldrichard19-LVD/pattern-mcp/main/.claude/skills/pattern-docs-sync/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/donaldrichard19-LVD/pattern-mcp

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 pattern-docs-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/donaldrichard19-lvd/pattern-mcp/pattern-docs-sync.svg)](https://agentmods.dev/skills/donaldrichard19-lvd/pattern-mcp/pattern-docs-sync)
Your own site
<a href="https://agentmods.dev/skills/donaldrichard19-lvd/pattern-mcp/pattern-docs-sync"><img src="https://agentmods.dev/badge/skills/donaldrichard19-lvd/pattern-mcp/pattern-docs-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,183 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 $0.00076 $0.01183
Opus 5 $0.00038 $0.00592
Sonnet 5 $0.00015 $0.00237
Haiku 4.5 $0.00008 $0.00118

Measured 2d ago against content hash bb20ea85da6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pattern-docs-sync 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.

.claude/skills/pattern-docs-sync/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pattern docs sync

Pattern keeps two published Artifacts that are supposed to track the repo, not drift from it. This skill is the checklist for keeping them honest. Both are owned by this user — update them in place via the Artifact tool's url param. Never publish a new artifact for either; that creates a second, disconnected URL.

  • Pattern Briefing — PM-facing positioning/architecture/risk brief. https://claude.ai/code/artifact/a87c4898-fa0f-4748-bc29-978ab9dd57be
  • Pattern Primer — engineering-facing doc explaining the reasoning behind Pattern's architecture: eight design principles, each tied to a real decision or finding, plus decision-rights and a glossary. https://claude.ai/code/artifact/2d064e6d-53d5-4a8f-9965-303364fd6985

Always Artifact action: "read" with the url first — republishing without reading the live version risks clobbering a change made outside this session, and the tool will refuse a stale publish anyway. Edit the saved local HTML file, then Artifact action: "publish" with file_path set to that same file and url set to the artifact's URL.

Rule 1 — new BACKLOG.md item → Pattern Briefing

Trigger: a new ## section is added to BACKLOG.md (a new feature idea, not a routine edit to an existing section).

  1. Read the Pattern Briefing artifact.
  2. Find the Opportunities section (<div class="ranked"> of .ranked-item.opportunity blocks, each <span class="rank-mark">NN</span>
    • <h4> + <p>). Append a new entry at the next rank number.
    • If the item is a genuine risk/concern rather than an upside, use the .ranked-item.risk variant instead if the section supports it — check how existing risk entries are marked in the Risks section and match that shape rather than forcing everything into Opportunities.
    • If it's better framed as an unresolved question than a proposed direction (e.g. something explicitly parked pending user demand), add it to Open questions to close instead — a plain <li>.
  3. Write the entry in the doc's own voice: plain business prose, no function/variable names, no raw markdown from BACKLOG.md pasted in. Translate "why this matters" into product/cost/quality terms a non-engineer reader would follow — see existing entries for the register (e.g. "Build a dedicated connection to each source — the long-term moat"). Carry over the backlog item's actual effort/priority framing (parked vs. active vs. sequenced) rather than implying it's imminent work if it isn't.
  4. Publish back to the same URL. Don't touch unrelated sections.

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 76 tokens per session scan A bb20ea85da6d

Subscribe to this mod's changes

pattern-docs-sync is a skill published in the GitHub repository donaldrichard19-LVD/pattern-mcp (4 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 1,183 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 2026-09-04.

Related

Other skills, from other repositories

clinical-case-report

Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…

nexu-io/open-design · 73 tokens

kami-deck

A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.

nexu-io/open-design · 49 tokens

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

fs-editorial-forest

Art-directing a fashion house's annual report — the editorial system, the photography rhythm, and the data spreads. Built as a decision-grade design craft deck for brand stakeholders, exec audience.

nexu-io/open-design · 44 tokens

html-ppt-zhangzara-pink-script

A wedding-anniversary tribute photo essay — a decade in scenes, the turning points, and the quiet meaning of staying. Built as a decision-grade story deck for couple, family, friends.

nexu-io/open-design · 50 tokens

html-ppt-zhangzara-stencil-tablet

A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.

nexu-io/open-design · 49 tokens