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/stencila/stencila/software-test-executionnpx skills add stencila/stencila --skill software-test-executiongit clone --depth 1 https://github.com/stencila/stencilaWhat 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 | $0.00097 | $0.02604 |
| Opus 5 | $0.00048 | $0.01302 |
| Sonnet 5 | $0.00019 | $0.00521 |
| Haiku 4.5 | $0.00010 | $0.00260 |
Grade A, and why
software-test-execution 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 2d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Execute scoped tests for a TDD slice and report structured results. This skill runs only the tests relevant to the current slice, parses the output, and reports a clear pass/fail result with details.
This skill does not write or modify any code or test files. It only reads, executes, and reports.
Required Inputs
This skill requires the following information to operate:
| Input | Required | Description |
|---|---|---|
| Test command | No | Command to run the scoped tests (discovered if not provided) |
| Test files | No | List of test file paths (used to scope the command if needed) |
| Slice scope | No | Description of what the slice covers (for context in the report) |
| Target packages | No | Packages, crates, or directories involved (for command discovery) |
| Slice name | No | Name or identifier of the current slice (for the report header) |
When used standalone, these inputs come from the user or the agent's prompt. When used within a workflow, the workflow's stage prompt will specify how to obtain them.
Outputs
After completing its work, this skill reports:
| Output | Description |
|---|---|
| Result | Whether the tests passed or failed (Pass / Fail) |
| Report | A structured report with counts, failure details, and notes |
Steps
1. Gather test metadata
Ensure the available inputs are collected:
- The test command is the primary input — if present, use it directly
- Test files and target packages are used as fallbacks for constructing a test command if no command is provided
- Slice name and scope provide context for the report
2. Determine the test command
What ships with it
2 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.
- 2d ago First seen · 247 lines · 97 tokens per session scan A a334884b074d
software-test-execution is a skill published in the GitHub repository stencila/stencila (900 stars, last pushed 3d ago), licensed Apache-2.0. It adds 97 tokens to every session and 2,604 once invoked, about $0.0005 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
rtk-tdd
Enforces TDD (Red-Green-Refactor) for Rust development. Auto-triggers on implementation, testing, refactoring, and bug fixing tasks. Provides Rust-idiomatic testing patterns with anyhow/thiserror, cfg(test), and Arrange-Act-Assert workflow.
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
test-driven-development
TDD workflow — Red, Green, Refactor cycle with practical examples.
Test Driven Development
Strict Red-Green-Refactor implementation methodology for high quality, regression-free software.
rtk-tdd
Enforces TDD (Red-Green-Refactor) for Rust development. Auto-triggers on implementation, testing, refactoring, and bug fixing tasks. Provides Rust-idiomatic testing patterns with anyhow/thiserror, cfg(test), and Arrange-Act-Assert workflow.
nw-at-completeness-check
Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.