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/red/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/red)<a href="https://agentmods.dev/skills/marcoemrich/exact-coding-exercises/red"><img src="https://agentmods.dev/badge/skills/marcoemrich/exact-coding-exercises/red/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/red"><img src="https://agentmods.dev/badge/skills/marcoemrich/exact-coding-exercises/red.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 | $0.00067 | $0.00528 |
| Opus 5.5 | $0.00027 | $0.00211 |
| Sonnet 5.5 | $0.00013 | $0.00106 |
| Haiku 4.5 | $0.00007 | $0.00053 |
Grade A, and why
red 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.
What it actually says
Red — one phase, manually driven
This is a manual phase control, not a separate method. It runs step 1 and step 2 of the predictive cycle and then stops. Use it when you want to steer Red-Green-Refactor yourself instead of invoking the whole
exact-codingworkflow. The method lives in one place; this skill only selects which part of it to execute now.
What to read
.claude/skills/predictive-tdd/SKILL.md— sections Core rules, 1. Activate one behavior and 2. Reach behavioral Red. Those are binding as written.- The matching profile under
.claude/skills/predictive-tdd/stacks/for inactive-test syntax and the commands to run. .claude/skills/exact-coding-shared/human-in-the-loop.mdfor the Red checkpoint and the prediction-mismatch rule.
If no ordered test list exists yet, say so and offer test-list first. Do not
invent a list as a side effect of this phase.
What to do
Execute exactly those two steps of the cycle, then stop:
- activate one behavior from the test list,
- predict the narrowest test's outcome, failure category, and message or values,
- run it and compare prediction with reality,
- add only enough scaffold to reach a behavioral failure, re-predicting each time.
Where to stop
Stop at the Red checkpoint from .claude/skills/exact-coding-shared/human-in-the-loop.md and report the active behavior, the
prediction, the actual result, and why this failure is the intended behavioral
Red. Do not write production behavior, and do not continue into Green — even
when the Autonomy Level would not stop there. The human invoked a single phase;
that invocation is the checkpoint.
If the activated test already passes, confirm that prediction, record that no production change is needed, and stop. Do not manufacture a failure.
On a prediction mismatch, follow Prediction mismatch in the Predictive TDD skill and stop there.
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 · 48 lines · 67 tokens per session scan A 6bca572b2626
red is a skill published in the GitHub repository marcoemrich/EXACT-Coding-Exercises (18 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 528 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 2026-09-20.
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.