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 igmarin/rails-agent-skills --skill plan-testsgit clone --depth 1 https://github.com/igmarin/rails-agent-skillsWrote 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/igmarin/rails-agent-skills/plan-tests)<a href="https://agentmods.dev/skills/igmarin/rails-agent-skills/plan-tests"><img src="https://agentmods.dev/badge/skills/igmarin/rails-agent-skills/plan-tests/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/igmarin/rails-agent-skills/plan-tests"><img src="https://agentmods.dev/badge/skills/igmarin/rails-agent-skills/plan-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 53 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 53 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 53 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00039 | $0.01276 |
| Opus 5 | $0.00019 | $0.00638 |
| Sonnet 5 | $0.00008 | $0.00255 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
plan-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 9d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Tests
Quick Reference
| Change type | First spec | Path | Why |
|---|---|---|---|
| API contract, params, status code, JSON shape | Request spec | spec/requests/ |
Proves the real HTTP contract |
| Domain rule on a cohesive record or value object | Model spec | spec/models/ |
Fast feedback on domain behavior |
| Multi-step orchestration across collaborators | Service spec | spec/services/ |
Focuses on the workflow boundary |
| Enqueue/run/retry/discard behavior | Job spec | spec/jobs/ |
Captures async semantics directly |
| Critical Turbo/Stimulus or browser-visible flow | System spec | spec/system/ |
Use only when browser interaction is the real risk |
| Engine routing, generators, host integration | Engine spec | spec/requests/ or engine path |
Normal app specs miss engine wiring — see test-engine |
| Bug fix | Reproduction spec | Where the bug is observed | Proves the fix and prevents regression |
HARD-GATE
CHECKPOINT: Test Design Review
1. Present: Show the failing spec(s) written
2. Ask:
- Does this test cover the right behavior?
- Is the boundary correct (request vs service vs model)?
- Are the most important edge cases represented?
- Is the failure reason correct (feature missing, not setup error)?
3. Confirm: Only proceed to implementation once test design is approved.
Core Process
Start at the highest-value boundary that proves the behavior with the least unnecessary setup.
Steps
- Name the behavior: State the user-visible outcome or invariant to prove.
- Locate the boundary: Decide where the behavior is observed first — HTTP request, service entry point, model rule, job execution, engine integration, or external adapter. Use the Quick Reference table to map the change type to the right spec type.
- Write one failing example: Keep it minimal; one example is enough to open the gate. List additional cases as follow-up coverage.
- Suggest the path: Name the likely spec path using normal Rails conventions (e.g.
spec/requests/...,spec/services/...,spec/jobs/...,spec/models/...). - Run and validate: Confirm the failure is because the behavior is missing, not because the setup is broken.
- Hand off: Continue with the skill that fits the slice —
write-testsfor general spec writing,test-servicefor service-layer coverage, ortest-enginefor engine integration.
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.
- 9d ago First seen · 122 lines · 39 tokens per session scan A c48dd5f905cc
plan-tests is a skill published in the GitHub repository igmarin/rails-agent-skills (24 stars, last pushed 18d ago), licensed MIT. It adds 39 tokens to every session and 1,276 once invoked, about $0.0002 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
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.