Borrowing it
Nothing to install: this file belongs to marcoemrich/EXACT-Coding-Exercises. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marcoemrich/EXACT-Coding-Exercises/main/.claude/skills/predictive-tdd/SKILL.mdgit clone --depth 1 https://github.com/marcoemrich/EXACT-Coding-ExercisesWrote 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/marcoemrich/exact-coding-exercises/predictive-tdd)<a href="https://agentmods.dev/skills/marcoemrich/exact-coding-exercises/predictive-tdd"><img src="https://agentmods.dev/badge/skills/marcoemrich/exact-coding-exercises/predictive-tdd/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/marcoemrich/exact-coding-exercises/predictive-tdd"><img src="https://agentmods.dev/badge/skills/marcoemrich/exact-coding-exercises/predictive-tdd.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 | $0.00069 | $0.01766 |
| Opus 5.5 | $0.00028 | $0.00706 |
| Sonnet 5.5 | $0.00014 | $0.00353 |
| Haiku 4.5 | $0.00007 | $0.00177 |
Grade A, and why
predictive-tdd 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Predictive Test-Driven Development
Use TDD as an empirical feedback loop: predict, check, compare, and let the evidence determine the next change.
Core rules
The prediction requirement applies only within the TDD workflow. Routine repository, file, and administrative operations do not require predictions.
- Work on exactly one observable behavior at a time.
- Before every deterministic check, state a concrete, falsifiable prediction and run the check immediately.
- Compare predicted and actual outcomes explicitly. Never rewrite an unexpected result as predicted.
- A valid Red fails because the active behavior is missing, for the predicted reason.
- Investigate prediction mismatches before changing production behavior.
- Implement only enough to satisfy the active behavior and keep previous behavior green.
- Refactor only while behavior tests are green.
- Do not invent unspecified behavior; resolve ambiguous observable contracts by stating the reading you adopt.
Preparation
Before the first cycle:
- Read the complete specification and identify every rule, example, boundary, and ambiguity.
- Create or review an ordered test list. Keep future tests inactive.
- Determine the project's stack and commands. If
stacks/contains a matching profile, read it before changing code. - Establish a baseline with the applicable behavior, compilation/type, lint, and smell checks. Predict each check before running it.
One predictive cycle
1. Activate one behavior
State its given/input, operation, and exact expected outcome in domain language. Choose the smallest public observation that proves it, then activate or write exactly one test.
2. Reach behavioral Red
Inspect the current code and predict the narrowest test's load/compile/execution outcome, failure category, and relevant message or values. Run it and compare.
If loading or compilation prevents the assertion from running, add only enough scaffold to reach the behavioral failure. Predict and check again. Do not implement the behavior until Red fails for the intended reason.
What ships with it
3 files 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.
- 1mo ago Changed f17f8451149d
- 1mo ago First seen · 138 lines · 69 tokens per session scan A f00ced4c6a06
predictive-tdd is a skill published in the GitHub repository marcoemrich/EXACT-Coding-Exercises (18 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,766 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 2026-09-17.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
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.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.