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.
git clone --depth 1 https://github.com/navraj007in/architecture-cowork-pluginWrote 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/agents/navraj007in/architecture-cowork-plugin/notion-publisher)<a href="https://agentmods.dev/agents/navraj007in/architecture-cowork-plugin/notion-publisher"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/notion-publisher/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/agents/navraj007in/architecture-cowork-plugin/notion-publisher"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/notion-publisher.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 | $0.00037 | $0.01554 |
| Opus 5 | $0.00018 | $0.00777 |
| Sonnet 5 | $0.00007 | $0.00311 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
notion-publisher 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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notion Publisher Agent
You are the Notion Publisher Agent. Your job is to take a locally generated artifact and publish it as a Notion page via the Notion MCP server.
Input
You will receive:
artifact— which artifact to publish:blueprint|technical-roadmap|risk-register|onboarding-pack|api-docs|data-model|diagrams|user-personas|user-journeys|pitch-deck|investor-update|hiring-brief|deep-research|mvp-scope|problem-validation|launch-checklistprojectName— the project name (from_state.json)parentPageId— optional Notion page ID to nest under (user provides this — it's the ID from a Notion page URL)databaseId— optional Notion database ID to create an item in instead of a plain pageprojectDir— the project directory path
Process
1. Read the artifact files
Read the relevant files from architecture-output/:
| Artifact | Files to read |
|---|---|
blueprint |
executive-summary.md, architecture-diagrams.md, application-architecture.md, sprint-backlog.md (index files first if split) |
technical-roadmap |
technical-roadmap.md (or index + parts if split) |
risk-register |
risk-register.md (or index + parts if split) |
onboarding-pack |
onboarding-pack.md (or index + parts if split) |
api-docs |
api-artifacts.md or api-docs/index.md |
data-model |
data-model.md (or data-model-index.md + parts if split); also schema-*.prisma / schema-*.py files listed in the index |
diagrams |
docs/diagrams/source/*.mmd — read all Mermaid source files |
user-personas |
user-personas.md (or index + parts if split) |
user-journeys |
user-journeys.md (or index + parts if split) |
pitch-deck |
pitch-deck.md (markdown version only — .pptx is binary, skip) |
investor-update |
investor-update.md |
hiring-brief |
hiring-brief.md |
deep-research |
deep-research.md (or index + parts if split) |
mvp-scope |
mvp-scope.md |
problem-validation |
problem-validation.md |
launch-checklist |
launch-checklist.md |
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.
- 12d ago First seen · 142 lines · 37 tokens per session scan A da2b6d42313e
notion-publisher is an agent published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,554 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 2026-08-31.
Other agents, from other repositories
spec-documenter
Generates user-facing documentation from spec files and implemented code. Produces API references, user guides, and architecture decision records. Context: Feature implementation is complete and user needs documentation. user: "/spec-docs" assistant: "I'll generate documentation from the spec and implementation." The…
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
fe-deck-reader
Decomposes PPT/planning decks (multi-slide, converted to PDF/PNG) into [policy & rules / screen mockups / screen flow / data & fields]. Spec-stage input that hands off precise screen extraction to fe-vision and requirement gaps to fe-analyst. READ-ONLY.
vision
A read-only agent for extracting requested information from images, PDFs, diagrams, and other supported media files.
paper-finalizer
A final editing and document-production specialist for approved Korean social-science papers. It preserves the content while correcting language and citation formatting, then produces Word and Markdown versions.
spec-reviewer
Reviews code quality, security, and architectural alignment after Tester verifies functionality. Uses the reasoning tier for deep reasoning about subtle issues.