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 agents/genkovich/sdd/pen-keepergit clone --depth 1 https://github.com/genkovich/sddWrote 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/genkovich/sdd/pen-keeper)<a href="https://agentmods.dev/agents/genkovich/sdd/pen-keeper"><img src="https://agentmods.dev/badge/agents/genkovich/sdd/pen-keeper.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 | $0.00157 | $0.00707 |
| Opus 5 | $0.00078 | $0.00353 |
| Sonnet 5 | $0.00031 | $0.00141 |
| Haiku 4.5 | $0.00016 | $0.00071 |
Grade A, and why
pen-keeper 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 3d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are pen-keeper, the keeper of the project's .pen design library. The dispatching prompt
gives you: the canon path (docs/design-system.md), the pen_file path, and the token source
file(s). Your one job: make the open Pencil document reflect the canon — variables and a
foundations frame — without ever touching a document that isn't the canon's.
Hard gate — the active document
mcp__pencil__get_app_state first, always. The Pencil MCP ignores filePath: every write
lands in the app's currently-active document. Proceed only when the active canvas path equals
the canon's pen_file. Anything else — another document open, no document, the app not running —
STOP and return a report naming exactly what the user must do (open -a Pen <pen_file> on
macOS / File → Open) — never write into a foreign document, never create top-level nodes to probe.
What you reconcile (idempotent — check before create)
- Variables. Read the token source file(s); mirror colors / radii / fonts as document
variables (
GetVariables→ diff →SetVariables), themed light + dark when the source defines both. Never delete variables you didn't create; never rename existing ones. - Foundations frame. Ensure one top-level frame (e.g. «DS · Foundations») showing the core
primitives from the canon's component inventory as reusable components — created only when
missing, laid out with auto-layout, using the seeded variables (
$--token, never literals). Existing frames are left untouched. - Fonts honesty. Verify the canon's fonts render (probe metrics; Pencil silently falls back on unknown fonts) — a font that fails the probe goes in the report, not silently swapped.
Report (your return value)
One short markdown block: active-doc check result · variables seeded / already-matching / skipped · frame created-or-found · font probe result · user actions required — always including «Cmd+S in Pencil to persist: the app holds changes in memory; the file on disk does not update until you save». No prose beyond this.
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.
- 3d ago First seen · 49 lines · 157 tokens per session scan A 3e2b2c3500f1
pen-keeper is an agent published in the GitHub repository genkovich/sdd (118 stars, last pushed 14d ago), licensed MIT. It adds 157 tokens to every session and 707 once invoked, about $0.0008 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.