Install
$ agentstack add skill-mrlarson2007-copilot-tdd-harness-tdd-green ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
TDD Green Phase Skill
Purpose
- Write the simplest code to make the failing test pass
- Do not modify tests in this phase
- No refactoring or generalization
- Commit after tests pass
Inputs
- Failing test id
- Skill and asset references
- Project code style patterns from
.github/instructions/tdd-patterns.instructions.md - Canonical GREEN style guide placeholder at
.github/skills/tdd-green/assets/project-code-style-patterns.md
Outputs
- Changed production files
- Test pass summary
Steps
- Load
.github/skills/tdd-green/assets/project-code-style-patterns.mdfirst, then load core asset files for minimal implementation, anti-patterns, and commit discipline - Check whether the RED test compiles.
- If the test references missing production symbols (types, methods, fields), the only allowed edit is the smallest possible compile-only stub — no behavior.
- Run the narrow test again. It must now compile and fail at runtime/assertion level before proceeding.
- This is the distinction between structural red (compile failure) and behavioral red (assertion failure). Both are RED; behavior must not be added until you are at behavioral red.
- Judge the next GREEN move before editing production code.
- Ask whether the change is the dumbest possible thing that makes only the current test pass.
- If the change also solves untested cases, tries to generalize, or looks like the feature instead of the slice, it is too broad.
- Prefer a constant, hardcoded branch, or the narrowest exact-case behavior the current test demands.
- Do not move from behavioral red into generalized implementation just because the change is small.
- Write minimal code to pass the test
- Use
tdd-test-runwith atest_run_requestcontract whose expected result is
a passing narrow check for the protected test or slice
- If the observed result does not match the expected GREEN outcome, revert only
the scoped production changes and return to the preceding GREEN decision point
- Run the broader validation required by project policy through
tdd-test-run
before reporting GREEN complete
- Return contract output
Completion Checks
- Only minimal code added
- All tests pass
- No test or refactor changes
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mrlarson2007
- Source: mrlarson2007/copilot-tdd-harness
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.