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/exact-coding-isolated-refactor/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/exact-coding-isolated-refactor)<a href="https://agentmods.dev/skills/marcoemrich/exact-coding-exercises/exact-coding-isolated-refactor"><img src="https://agentmods.dev/badge/skills/marcoemrich/exact-coding-exercises/exact-coding-isolated-refactor/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/exact-coding-isolated-refactor"><img src="https://agentmods.dev/badge/skills/marcoemrich/exact-coding-exercises/exact-coding-isolated-refactor.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 | $0.00766 |
| Opus 5.5 | $0.00032 | $0.00306 |
| Sonnet 5.5 | $0.00016 | $0.00153 |
| Haiku 4.5 | $0.00008 | $0.00077 |
Grade A, and why
exact-coding-isolated-refactor 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.
This is a copy
89% identical to exact-coding — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EXACT Coding — Predictive TDD v1 — Isolated Refactor
This is the consumer form of the universal EXACT Coding Predictive-TDD line. It runs in one shared context: Test List once, then one-test Red-Green-Refactor cycles. Refactoring uses the Four Rules of Simple Design in an isolated subagent. Refactoring also applies a domain-responsibility review and a mandatory concrete boundary trial whenever it finds a credible semantic seam. This profile deliberately has no APP calculation or metric-driven end pass.
Preparation
- Read
.claude/skills/test-list/SKILL.md. - Read
.claude/skills/predictive-tdd/SKILL.md. - Determine the project's language and test framework. Read the matching file
under
.claude/skills/predictive-tdd/stacks/before changing code. - Read the complete specification and establish the applicable baseline gates.
Do not assume TypeScript or Vitest from this orchestration file. Concrete inactive-test syntax, examples, paths, commands, compiler behavior, and quality tools belong only to the selected stack profile.
Sequence
- Create the complete ordered test list with every future behavior inactive, then predict and verify that the inactive list leaves the full suite green.
- Apply the Test-List checkpoint from
.claude/skills/exact-coding-shared/human-in-the-loop.md. - For exactly one behavior at a time, follow the Predictive TDD skill:
- activate one behavior and reach behavioral Red,
- state falsifiable predictions before deterministic checks and compare them explicitly with reality,
- apply the Red checkpoint,
- reach Green with the smallest production change,
- after every Green, delegate the Four Rules review through the Agent tool with
subagent_type: refactor; invoke it even when Green changed no production code, - perform the mandatory domain-boundary trial and retain or narrowly undo it based on semantic and test evidence,
- apply the Refactor checkpoint.
- Continue until every listed behavior is executable and all applicable gates from the active stack profile pass.
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 · 64 lines · 79 tokens per session scan A d8afd06ed5cc
exact-coding-isolated-refactor is a skill published in the GitHub repository marcoemrich/EXACT-Coding-Exercises (18 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 766 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to exact-coding, differing in 12 lines, and is treated as a copy.
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.