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 X-School-Academy/skill-pilot --skill test-number-workflowgit clone --depth 1 https://github.com/X-School-Academy/skill-pilotWrote 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/x-school-academy/skill-pilot/test-number-workflow)<a href="https://agentmods.dev/skills/x-school-academy/skill-pilot/test-number-workflow"><img src="https://agentmods.dev/badge/skills/x-school-academy/skill-pilot/test-number-workflow/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/x-school-academy/skill-pilot/test-number-workflow"><img src="https://agentmods.dev/badge/skills/x-school-academy/skill-pilot/test-number-workflow.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 | $0.00043 | $0.00462 |
| Opus 5.5 | $0.00017 | $0.00185 |
| Sonnet 5.5 | $0.00009 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
test-number-workflow 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 16d 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.
What it actually says
AI Builder - Test Number Workflow
Generate, combine, and inspect simple number/string values for workflow execution tests.
When to Use This Skill
- A workflow test node needs a random numeric result.
- A workflow test node needs a random string result.
- A workflow test node needs to concatenate a number and a string.
- A workflow test node needs to inspect text and return digits or
string. - A workflow needs downstream-friendly plain-text outputs.
Your Roles in This Skill
- Backend Developer (Engineer): Produce deterministic-format outputs for the requested test action.
- QA Engineer: Keep outputs simple, parseable, and suitable for downstream workflow nodes.
Role Communication
As an expert in your assigned roles, you must announce your actions before performing them using the following format:
As a {Role, and Role-XYZ if have more roles}, I will {action description}
This communication pattern ensures transparency and allows for human-in-the-loop oversight at key decision points.
Instructions
Follow these steps in order:
Step 1: Select the Test Action
- If the task asks for a random number, use
references/random-number.md. - If the task asks for a random string, use
references/random-string.md. - If the task asks to concatenate a number and string, use
references/concat-number-string.md. - If the task asks to detect, inspect, or extract numbers from text, use
references/detect-number.md.
Step 2: Load the Needed Reference
Open only the reference file for the selected action.
Step 3: Return the Result
Output result as plain text. If the user asked to save it to a file, write it there.
Unless the selected action explicitly says otherwise, return only the generated or derived value with no labels, bullets, code fences, or explanation.
Expected Output
- A random integer.
- A random alphanumeric string.
- A concatenated number-string value.
- Extracted digits, or
stringwhen no digits exist.
What ships with it
4 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.
- 16d ago First seen · 58 lines · 43 tokens per session scan A 668b7ca52baa
test-number-workflow is a skill published in the GitHub repository X-School-Academy/skill-pilot (20 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 462 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 2026-10-02.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
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.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
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.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.