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 cajasmota/grafel --skill grafel-test-pagegit clone --depth 1 https://github.com/cajasmota/grafelWrote 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/cajasmota/grafel/grafel-test-page)<a href="https://agentmods.dev/skills/cajasmota/grafel/grafel-test-page"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-test-page/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/cajasmota/grafel/grafel-test-page"><img src="https://agentmods.dev/badge/skills/cajasmota/grafel/grafel-test-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.02404 |
| Opus 5.5 | $0.00018 | $0.00962 |
| Sonnet 5.5 | $0.00009 | $0.00481 |
| Haiku 4.5 | $0.00005 | $0.00240 |
Grade A, and why
grafel-test-page 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grafel-test-page
Single-entity docgen smoke test with full emit→fill→apply roundtrip in one invocation.
This skill drives the complete grafel docgen LLM-mode loop — emit, fill (YOU are the LLM), and apply — on a single entity, in one natural-language invocation. No manual command-construction or copy-paste of paths or schema instructions required.
When to use this skill
Invoke when the user asks for any of:
- "Test docgen on
<entity>." - "Smoke-test docgen for
<entity>in group<group>." - "Iterate on docgen prose for X."
- "Run /test-docgen-page" or "/grafel-test-page" (slash commands).
- "Check the emit→fill→apply roundtrip for
<entity>."
Scope: this skill operates on ONE entity per invocation. It is designed for debugging and iteration — verifying the roundtrip, tuning guidance prose, and catching contract failures on a specific node.
For production multi-entity docgen across a full group, use the generate-docs skill instead. That skill runs Passes 0–20 across every entity in the group; this skill runs a single entity to tight iteration speed.
Inputs
Parse from the invocation text. Only prompt the user when a required field is genuinely ambiguous.
| Input | Required | Default | Notes |
|---|---|---|---|
group |
yes | — | e.g. acme, grafel, polyglot-platform |
entity |
yes | — | Prefixed ID (acme-core::<hex>), raw 16-char hex, or free-text query |
tier |
no | 1 |
0 = single-section, 1 = single-page |
section |
only when tier=0 | — | Section name from KnownSections (e.g. overview, flows) |
output-dir |
no | /tmp/docgen-test-<RFC3339-timestamp>/ |
Where emit, bundle, result, and final page land |
show-stub |
no | false |
If true, print first 30 lines of stub-page.md after emit |
Construct the RFC3339 timestamp for the default output-dir at invocation time (e.g. 2026-05-23T14:05:00Z). Never reuse a previous output-dir unless the user explicitly provides one.
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 · 222 lines · 46 tokens per session scan A 20e0dc65d955
grafel-test-page is a skill published in the GitHub repository cajasmota/grafel (24 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,404 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.