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 axiomantic/spellbook --skill isolated-testinggit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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/axiomantic/spellbook/isolated-testing)<a href="https://agentmods.dev/skills/axiomantic/spellbook/isolated-testing"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/isolated-testing/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/axiomantic/spellbook/isolated-testing"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/isolated-testing.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 | $0.00078 | $0.01999 |
| Opus 5.5 | $0.00031 | $0.00800 |
| Sonnet 5.5 | $0.00016 | $0.00400 |
| Haiku 4.5 | $0.00008 | $0.00200 |
Grade A, and why
isolated-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 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Isolated Testing
Uncertainty is not uncomfortable. Uncertainty is the natural state before knowledge. You do not rush to escape it. You sit with it, design a proper test, and let evidence speak.
This discipline is critical to my career.
You are here because you have theories to test. Not to thrash. Not to "try things." To TEST, methodically.
Invariant Principles
- One Theory, One Test, Full Stop. Test a single theory completely before considering another. No mixing. No "while I'm here."
- Design Before Execute. Write the repro test encompassing every step. Get approval (unless autonomous). THEN run.
- Stop on Reproduction. Bug repros = STOP investigating. Announce. Wait (unless autonomous, then proceed to fix phase).
- Uncertainty is Not Urgency. The pressure to "do something" is the enemy. Deliberation resolves uncertainty.
- Evidence is Binary. Repro or no-repro. Proved or disproved. No "partially confirmed."
- Know Your Code State. Before EVERY test: verify baseline, what modifications exist, what state you intend to test.
- Queue Discipline. Test theories in order. No skipping. No adding new theories mid-test.
The Protocol
Step 0: Verify Code State
CODE STATE CHECK:
- Baseline: [commit SHA / version / description]
- Current state: [clean / modified]
- Modifications: [none / list what's changed]
- Intended test state: [clean baseline / with modification X]
If you don't know your code state, STOP. Return to clean baseline before proceeding.
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 · 255 lines · 78 tokens per session scan A b42fab97b8f3
isolated-testing is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 1,999 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 2026-09-03.
Other skills, from other repositories
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.
isolate-the-specific-failure-mode-before-proposing-a-fix
When delegating a task affected by this skill, include.
debug
Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be reproduced and proven before any fix. On-demand; callable mid-implement. NOT a feature to spec or build (that is specify/implement), NOT the lint/test gate (that is verify), NOT adversarial diff…
qa-sweep
Codex adapter for independent QA review of opencode-swarm changes. Use after implementation or debugging when the user asks for a QA sweep, regression check, review pass, quality gate, or confidence check before publishing.