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 skills add magnus919/agent-skills --skill cryptpadgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/skills/magnus919/agent-skills/cryptpad)<a href="https://agentmods.dev/skills/magnus919/agent-skills/cryptpad"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/cryptpad/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/skills/magnus919/agent-skills/cryptpad"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/cryptpad.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 | $0.00076 | $0.01273 |
| Opus 5.5 | $0.00030 | $0.00509 |
| Sonnet 5.5 | $0.00015 | $0.00255 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
cryptpad 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CryptPad
When not to use
- For local office-file creation or conversion, use
documentsoranydoc. - For general API contract design, use
api-design-and-evolution. - For container operations, use
docker-compose; keep CryptPad-specific configuration here. - EncryptPad is a different OpenPGP desktop application.
Workflow
- Establish the instance origin, deployed version, document application, and task: existing CryptDrive content, embedding an externally stored document, or instance operations. Never infer rights from a title, successful HTTP request, or editor UI alone.
- Read architecture and interface boundaries for feasibility. Prefer the documented browser integration API for external storage; use an authorized browser session for existing CryptDrive documents. Do not invent bearer-token CRUD routes.
- For public instance discovery, run the CLI below. For an embed, read integration contracts, then use the adapter and plan templates. For self-hosting failures, read operations.
- This skill can guide actions that change external state: editing, importing, sharing, key rotation, deployment and retention changes. Confirm the target, scope, and rollback path before acting. Read-only discovery may proceed without confirmation. Use existing explicit authorization when it covers these details. Destructive operations still require an explicit user directive. Prepare reversible work before escalating gaps.
- Verify the result on the normal browser path: document loads, edits synchronize, the save reaches durable storage, and a fresh session reopens the saved content. Check view-only access with a real view key. HTTP discovery is not this verification.
- Deliver the artifact or diagnosis, with version/source evidence, tests actually run, and remaining limitations. Stop after three non-converging diagnostic passes and report the exact failed boundary and next required evidence. Do not substitute raw ciphertext for exported document content or claim a schema-valid eval proves runtime behavior.
What ships with it
12 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.
- evals/evals.json 3.8 KB
- evals/trigger-queries.json 500 B
- README.md 2.0 KB
- references/architecture.md 4.0 KB
- references/integration.md 4.9 KB
- references/operations.md 3.1 KB
- references/sources.md 3.8 KB
- scripts/cryptpad.py 5.9 KB runs code
- scripts/test_cryptpad.py 5.6 KB runs code
- templates/browser-integration.md 1.8 KB
- templates/integration-adapter.mjs 1.2 KB runs code
- templates/integration-plan.md 1.5 KB
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.
- 1mo ago First seen · 101 lines · 76 tokens per session scan A 73ce3c6fa4c8
cryptpad is a skill published in the GitHub repository magnus919/agent-skills (133 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 1,273 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
meter-invoice
Generate CocoMeter chargeback invoices. Usage: $meter invoice.
review-export
Export CocoReview reports as markdown, html, or pdf-ready status artifacts. Usage: $review export markdown|html|pdf [report-path].
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
svg-chart
Render data into a standalone SVG chart file — bar, line, or pie. Use when the user provides numbers (inline, JSON, or CSV) and asks for a chart, graph, plot, trend, comparison, breakdown, or any visual summary of the data. Produces a self-contained .svg viewable in any browser; no external libraries required.
create-md-from-browsermcp-snapshot
Extracts and converts BrowserMCP accessibility tree snapshots into clean, high-fidelity Markdown documents with correct structures (headings, lists, tables, blockquotes, formatting, and links). Use when the user asks to create a markdown document from a webpage; especially if they ask to do it with BrowserMCP.
redline
Use when a markdown plan, spec, or doc should be opened in the Redline review UI for the user. The agent launches the CLI; do not only paste instructions for the user to run manually.