Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pssah4/digital-innovation-agentsnpx agentmods add skills/pssah4/digital-innovation-agents/testingWrote 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/pssah4/digital-innovation-agents/testing)<a href="https://agentmods.dev/skills/pssah4/digital-innovation-agents/testing"><img src="https://agentmods.dev/badge/skills/pssah4/digital-innovation-agents/testing.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 5.1 | $0.00063 | $0.02811 |
| Opus 5 | $0.00032 | $0.01406 |
| Sonnet 5 | $0.00013 | $0.00562 |
| Haiku 4.5 | $0.00006 | $0.00281 |
Grade A, and why
testing 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 7d 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing -- Unit & Integration Tests
Creates tests that fit into the existing codebase. Detects the framework, patterns, and conventions automatically from the project.
Writing style and frontmatter rules:
See skills/project-conventions/SKILL.md#canonical-specs (Writing style,
Frontmatter spec).
MANDATORY Pre-Phase 0: Branch and item check
Standard ritual, full rules in
skills/project-conventions/references/team-workflow.md: identify the
active item (tests usually continue on the same FEAT/FIX/IMP branch),
verify the branch matches <type>/<item-id-lower>-<slug>
(AskUserQuestion on mismatch), run flow.py create-issue +
open-draft-pr when GitHub sync is on, tag the phase at ritual end
(--phase test), and write .git/dia-active-skill.
MANDATORY Phase 0: Artifact triage
New tests bind to an existing FEATURE, IMP, or FIX id. Exception: read-only analysis (coverage report, gap identification, reading existing tests) does not need triage.
If the binding cannot be derived from the prompt, ask once before the first new test (user's working language):
"Does this test run belong to a FEATURE, an IMP, or a FIX? Please name the ID."
Triage details:
skills/project-conventions/references/graph-invariants.md, section
"Artifact triage at entry point".
MANDATORY: Verify gate language
/testing shares the verify gate with /coding. No completion claim
without fresh verification evidence in the current message.
Hard threshold for "all green": 0 test failures, 0 lint errors (if lint
runs in the suite), coverage not regressed (line/branch/function each at
or above the project target from _devprocess/rules/technical.md or
Coverage section).
Forbidden without fresh verification: "should pass", "tests should be green now", "looks good", "probably fine". The skill executes the test command IN THIS MESSAGE before any completion claim. Cached output and stale logs are not evidence.
Codebase analysis first
Before writing tests, scan the project for:
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.
- 7d ago First seen · 341 lines · 63 tokens per session scan A 60baa7b701dc
testing is a skill published in the GitHub repository pssah4/digital-innovation-agents (39 stars, last pushed 26d ago), licensed MIT. It adds 63 tokens to every session and 2,811 once invoked, about $0.0003 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
verification-protocol
How to prove a hypothesis is TRUE or FALSE using Move unit tests.
smoke-test-database
Quick Reference - Load this first for fast context (3KB).
ExUnit Test Framework
Execute and generate ExUnit tests for Elixir projects with setup callbacks, describe blocks, and async testing support.
Jest Test Framework
Execute and generate Jest tests for JavaScript/TypeScript projects with support for unit, integration, and E2E testing.
pytest Test Framework
Execute and generate pytest tests for Python projects with fixtures, parametrization, and mocking support.
RSpec Test Framework
Execute and generate RSpec tests for Ruby projects with let bindings, before hooks, and mocking support.