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 xD4O/praxis --skill testing-strategygit clone --depth 1 https://github.com/xD4O/praxisWrote 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/xd4o/praxis/testing-strategy)<a href="https://agentmods.dev/skills/xd4o/praxis/testing-strategy"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/testing-strategy/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/xd4o/praxis/testing-strategy"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/testing-strategy.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 | $0.00072 | $0.01236 |
| Opus 5.5 | $0.00029 | $0.00494 |
| Sonnet 5.5 | $0.00014 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
testing-strategy 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 15d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Strategy Protocol
EXTREMELY_IMPORTANT: This is a MANDATORY protocol, not a suggestion. Follow every step. Do not skip steps. Do not combine steps. Do not summarize. Work through each gate in order.
You are deciding WHAT to test and HOW — before writing tests. Do NOT open a test file yet. Tests written without a strategy verify what the code does, not what it must do.
STEP 1 — Classify what is being tested
For each unit of work, classify it as exactly ONE of these. The test type follows:
| Subject | Signature | Right test type |
|---|---|---|
| PURE-LOGIC | Deterministic input→output, no side effects | Unit tests, edge-case tables |
| I/O-BOUNDARY | Talks to disk, network, DB, clock, env | Contract test + fake/double at the seam |
| INTEGRATION | Multiple components must agree | Few end-to-end paths through real wiring |
| REGRESSION | A specific past bug must never return | One test that reproduces that exact bug |
State the classification explicitly. If a unit mixes types (logic tangled with I/O), that is a design finding — flag it; the seam may need extracting before it is testable.
STEP 2 — Rank failure modes by value
List the ways this code can fail that would actually hurt: data loss, wrong money math, silent corruption, security bypass, crash on common input. Rank by damage × likelihood.
Write tests top-down from this list. Coverage percentage is NOT a goal — a suite that covers 60% including every ranked failure mode beats 95% of asserting getters. If you catch yourself adding a test only to move a coverage number, delete it and return here.
STEP 3 — For bug fixes: regression test FIRST
If this work fixes a bug, this step is not optional:
- Write a test that reproduces the reported bug.
- Run it against the OLD (unfixed) code — confirm it FAILS. If it passes, it does not capture the bug; rewrite it until it fails for the bug's reason.
- Apply/keep the fix. Confirm the same test now PASSES.
The fail-then-pass sequence must be observed, not assumed. A fix without this test is a fix that can silently regress.
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.
- 15d ago First seen · 110 lines · 72 tokens per session scan A e480da04b1cd
testing-strategy is a skill published in the GitHub repository xD4O/praxis (28 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 1,236 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 2026-10-02.
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.