aktonay/skillz / skills/agent-harness/ecc
ecc
VerifiedEverything Claude Code (ECC) / Agent Harness OS. Imposes a disciplined, multi-step engineering pipeline (plan, test, implement, review, verify, remember) with strict verification gates, memory persistence, and anti-slop rules.
ECC (Everything Claude Code) — Agent Harness Operating System
ECC acts as a persistent middle layer that forces coding agents to follow rigorous software engineering practices instead of improvising or writing unverified code.
The ECC Gated Pipeline
Agents running under the ECC harness must follow this immutable sequence:
- Reconnaissance & Contract:
- Inspect existing architecture, test suites, and contracts before touching any files.
- Establish explicit acceptance criteria.
- Test-Driven Gating (Failing Tests First):
- Write failing automated tests (or reproducer scripts) before generating production code.
- No code generation is approved without a verified red test.
- Scoped Implementation:
- Write the minimum necessary changes to pass the test.
- Stay strictly within the declared write scope.
- Autonomous Verification:
- Run the full test suite, linter, and type checker.
- Verify that test output passes (Green).
- Architectural & Security Audit:
- Check against known vulnerability vectors and agent anti-patterns.
- Memory & Reflection:
- Persist key architectural decisions and failure recoveries for future sessions.
Commands & Workflows
/plan: Create structured step-by-step implementation contracts./verify: Run multi-agent automated review and evidence verification./remember: Store repo-specific constraints into project context memory.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 318k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 318k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 318k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |