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/miaodx/intuitive-flow/intuitive-testsnpx skills add MiaoDX/intuitive-flow --skill intuitive-testsgit clone --depth 1 https://github.com/MiaoDX/intuitive-flowWrote 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/miaodx/intuitive-flow/intuitive-tests)<a href="https://agentmods.dev/skills/miaodx/intuitive-flow/intuitive-tests"><img src="https://agentmods.dev/badge/skills/miaodx/intuitive-flow/intuitive-tests.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 | $0.00154 | $0.03034 |
| Opus 5 | $0.00077 | $0.01517 |
| Sonnet 5 | $0.00031 | $0.00607 |
| Haiku 4.5 | $0.00015 | $0.00303 |
Grade A, and why
intuitive-tests 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 3d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intuitive Tests
Use this skill to make a test suite easier to understand, faster to run, and less coupled to implementation details. The goal is not "more tests." The goal is a smaller, cleaner suite where each test has an obvious reason to exist and future contributors can tell what behavior the suite protects.
Existing tests are not grandfathered in. If a current unit test cannot name the project logic, caller-visible behavior, meaningful failure mode, or real contract it protects, remove it, merge it into a stronger behavior test, or reclassify it to the correct layer. Treat structure-only, metadata-only, wiring-only, implementation-shape, and "coverage went up" tests as debt by default, not as weak tests to tolerate.
The workflow is framework-agnostic, but the examples assume Python/pytest.
Bounded Proposal Rule
For broad or ambiguous cleanup, audit first and stop after a decision-complete proposal. Do not move files, delete tests, rewrite guidance, or edit production code until the target slice, accepted value gate, evidence level, and stop condition are explicit.
For a precise target where the user asks for implementation, apply one coherent vertical slice. Keep newly discovered unrelated ideas parked instead of letting the work expand by drift.
For test-suite cleanup, a good proposal lets the user choose between conservative, pruning-first, layout-first, or fixture-extraction paths. The default recommendation should be pruning-first when the suite is full of tiny, shape-oriented, or redundant UTs. Marker/layout work is a support move, not a substitute for improving test value.
Verification skips are repo truth, not reusable skill truth. If some tests must not run because of network, credentials, simulator, hardware, paid APIs, or local services, derive the skip from the user's prompt and repo instructions, then report those skipped checks explicitly.
Core Principles
Prefer tests that verify observable behavior through public interfaces.
Do not add or keep a UT just because code exists, a branch changed, or coverage is desired. A UT earns its place only when it can answer all five admission questions:
What ships with it
1 file 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.
- 3d ago First seen · 290 lines · 154 tokens per session scan A d5cb06ccd376
intuitive-tests is a skill published in the GitHub repository MiaoDX/intuitive-flow (48 stars, last pushed 8d ago), licensed MIT. It adds 154 tokens to every session and 3,034 once invoked, about $0.0008 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
bug-fix-protocol
8-step disciplined bug-fix protocol that treats every production bug as two failures — the code defect itself and the testing system that allowed it through. Use when fixing a production bug, investigating a regression, writing a post-mortem, or auditing a missed defect. Triggers on "fix this bug", "production bug"…
release
Create a new release with version bump, release notes, commit, and tag.
sub-tasks
View and manage SubFrame Sub-Tasks. Use when starting work, completing tasks, checking what's pending, or creating new tasks from conversation.
sub-audit
Run a code review and documentation audit on recent changes. Finds bugs, edge cases, missing docs, and type safety issues.
sub-docs
Sync all SubFrame documentation after feature work. Updates AGENTS.md lists, changelog, PROJECTNOTES decisions, and STRUCTURE.json.
sub-ipc
Regenerate the IPC channel reference documentation from ipcChannels.ts type maps.