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 johanthoren/jeff --skill testinggit clone --depth 1 https://github.com/johanthoren/jeffWrote 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/johanthoren/jeff/testing)<a href="https://agentmods.dev/skills/johanthoren/jeff/testing"><img src="https://agentmods.dev/badge/skills/johanthoren/jeff/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/johanthoren/jeff/testing"><img src="https://agentmods.dev/badge/skills/johanthoren/jeff/testing.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 | $0.00079 | $0.01258 |
| Opus 5.5 | $0.00032 | $0.00503 |
| Sonnet 5.5 | $0.00016 | $0.00252 |
| Haiku 4.5 | $0.00008 | $0.00126 |
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 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Standards
Language-agnostic defaults. Language-specific skills override where they conflict.
Golden Rule: If you can't test it easily, refactor it.
Structure and Naming
- Arrange, act, assert: set up the data, execute the code, verify the result. One behavior per test.
- Names state the expectation:
validateEmail returns false for invalid format, notit worksortest user.
What to Test
- DO: happy path; edge cases (boundaries, empty, null); error cases (invalid input, failures); business logic; public APIs.
- DON'T: third-party libraries; framework internals; simple getters/setters; private implementation details.
Coverage
Coverage is an outcome of testing the right intersections, not a target to chase. Not every line, and not every one-liner, needs a test; a one-line pass-through does not. Cover each behavior and its real edges; a task's acceptance criteria are the floor.
Principles
- Test behavior, not implementation: focus on what, not how. Assert results, never that a mock was called with particular arguments:
expect(mock).toHaveBeenCalledWith(...)pins procedure and goes red on a behavior-preserving refactor. - Would it survive a refactor? If a behavior-preserving refactor would turn the test red, it tests procedure; rewrite it to assert the result. Procedure-coupled tests lock in design flaws.
- Mock through injected boundaries: dependency injection makes a hand-rolled fake (
{ findById: () => fixture }) sufficient; no framework magic required. - Independent tests: no shared state, any order, one assertion's worth of behavior each.
- Fast and reliable: run tests frequently; fix failures immediately.
Change-Detector Tests Are a Banned Smell
A change-detector test asserts a value or call shape that no consumer observes, so it goes red on any edit to that value and catches no regression the edit would not. It is configuration duplicated into the test as a second place to edit. Do not write one.
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 · 62 lines · 79 tokens per session scan A cdf8fcfb06a8
testing is a skill published in the GitHub repository johanthoren/jeff (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,258 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 2026-08-31.
Other skills, from other repositories
archetype-lint
This skill should be used when the user asks to "lint an archetype", "validate an archetype", "check archetype compliance", "check archetype rules compliance", or "run archetype rules". Applies 24 normative lint rules with ERROR/WARNING/INFO severity. Supports STRICT and PERMISSIVE modes. Reports violations only — it…
grade-iterate
Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader), read each verdict, decide the next move (sharpen / re-run / promote to schedule), and once a version passes, run held-back eval cases in parallel. Use when the…
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
lab:autoresearch
Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.