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 agentmods add skills/backnotprop/plannotator/plannotator-visual-explainernpx skills add backnotprop/plannotator --skill plannotator-visual-explainergit clone --depth 1 https://github.com/backnotprop/plannotatorWhat 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 | $0.00078 | $0.01467 |
| Opus 5 | $0.00039 | $0.00733 |
| Sonnet 5 | $0.00016 | $0.00293 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
plannotator-visual-explainer 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- plannotator-visual-explainer — 94% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plannotator Visual Explainer
Three paths depending on content type. Each has its own references and structure.
Route by content type
Implementation plan, design doc, or proposal → Follow the Plan path. Read references/design-system.md and references/svg-patterns.md. Prescriptive structure.
PR explainer, diff review, or code change walkthrough → Follow the PR path. Read references/design-system.md and references/pr-components.md. Prescriptive structure.
Everything else (architecture diagrams, data tables, slide decks, project recaps, general visual explanations) → Follow the Visual explainer path. Delegates to nicobailon/visual-explainer with Plannotator theme tokens.
Delivery
Always deliver via Plannotator's annotation UI. Do NOT use open or xdg-open.
For any deliverable that uses Mermaid, render every diagram with Mermaid 11 in both the light
and dark palettes before opening the annotation UI. Rendering is a hard gate: an exception,
empty SVG, or error output such as aria-roledescription="error" or Syntax error in text
means the explainer is not deliverable. Fix the diagram or theme configuration and rerun both
palettes until every SVG passes.
Plans/proposals (user should approve/deny):
plannotator annotate <file> --gate
Everything else (informational):
plannotator annotate <file>
Plan path
For implementation plans, design docs, feature specs, migration guides, and proposals.
Before generating, read:
references/design-system.md— Plannotator theme tokens, typography, component patternsreferences/svg-patterns.md— inline SVG building blocks for architecture diagrams, flowcharts, data flow
Document structure (in order, pick what fits):
- Header — eyebrow label (mono, uppercase), title (serif, large), prompt box (the original brief)
- Summary strip — 3-5 stat cards showing key numbers at a glance (components, endpoints, tables, etc.)
- Milestones / timeline — vertical timeline showing phases without time estimates. Phases show sequence and dependencies, not duration.
- Architecture / data flow — inline SVG diagram. Use for 3+ interacting components. Highlighted boxes for new components, dashed arrows for async paths.
- Mockups — build UI mockups in HTML/CSS directly, not as descriptions
- Key code — dark-theme code blocks with syntax highlighting. Only architecturally significant interfaces/schemas — not every function.
- Risks & mitigations — table with severity badges (HIGH/MED/LOW)
- Open questions — callout cards with decision owner ("Decide with: backend team")
What ships with it
5 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.
- yesterday First seen · 118 lines · 78 tokens per session scan A 915b90901bce
plannotator-visual-explainer is a skill published in the GitHub repository backnotprop/plannotator (8,256 stars, last pushed 2d ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,467 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 2026-08-30.
Other skills, from other repositories
cache-notes
Fetch & embed AI transcripts as Obsidian callouts. Args: , all, refresh . Prompts for URLs if empty.
recap
Produce a weekly/date-range recap from emails, Slack, Jira/Confluence, and vault notes. Args: [dates]. Default = this week.
fill-participants
Resolve and fill Participants frontmatter + link unlinked names in body. Args: , all.
followup-todos
Extract action items as plain markdown bullets (with confirmation). Args: . No args = run /note-status pending --step=todos.
meeting
Create or wrap meeting notes. Args: {title} [folder=X], wrap , wrap pending [today|this week|dates]. No args = pick from Google Calendar.
note-status
Verify meeting notes are fully processed. Args: , [dates], all, pending [dates] [--step=X]. Shows which wrap steps are complete or missing.