Agent Ready By Sero
Description
Makes your codebase agent-friendly and keeps it that way. Small files so agents don't waste tokens. CLAUDE.md in every directory so they don't have to guess. Tests so they check their own work. Run once, it bolts rules into your global config — every project enforces standards automatically.
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
Agent Ready by Sero
Makes your codebase agent-friendly and keeps it that way. Two modes — a quick structural lint for daily use, and a deep scan with auto-fixing for when you're serious.
Two Modes
`/agent-ready` — Quick Mode (default)
6-check structural lint. Fast, report-only. Use it anytime.
| Check | What It Flags |
|---|---|
| File sizes | Source files over 300 lines |
| Directory bloat | Directories with 20+ files |
| Agent context | Missing CLAUDE.md files in root + key subdirectories |
| Type safety | any sprawl (TS), # type: ignore (Python), interface{} (Go) |
| Linting | Missing linter config |
| Test patterns | Test-to-source ratio below 1:5 |
Output: PASS/WARN/FAIL per check, priority fixes, offer to fix.
`/agent-ready full` — Full Mode
20 criteria across 5 pillars. Maturity levels L1-L5. Improvement plan. Auto-fixing.
**The 5 Pillars:**
| Pillar | What It Checks |
|---|---|
| Feedback Loops | Build command, test command, linter, formatter, type checking, pre-commit hooks |
| Structure | File sizes, directory sizes, lock file, type safety violations |
| Documentation | CLAUDE.md/AGENTS.md, subdirectory context, README setup, .env.example, .gitignore |
| Testing | Tests exist, test-to-source ratio, test patterns |
| Safety | No hardcoded secrets, dependency update automation |
**Maturity Levels:**
| Level | Name | What It Means |
|---|---|---|
| L1 | Functional | Can build, has basics (linter, lock file, README, .gitignore, tests exist) |
| L2 | Documented | Agent can understand the project (CLAUDE.md, type checking, pre-commit hooks, env docs) |
| L3 | Agent-Ready | Agent can work effectively (tests runnable, small files, subdir context, good test ratio) |
| L4 | Optimized | Agent works with confidence (formatter, test patterns, no secrets, dep updates) |
| L5 | Exemplary | Everything dialed |
**L3 is the target for most projects
Related Skills
Auto Update
Pull the latest ECC repo changes and reinstall the current managed targets.
Ecc Guide
Navigate ECC's current agents, skills, commands, hooks, install profiles, and docs from the live repository su
Epic Claim
Claim an epic issue, stamp coordination state, and sync local ownership.
Epic Publish
Publish a validated epic update back to the issue and local cache.
Epic Review
Mark epic review requested, approved, or changes requested.
Epic Unblock
Sweep blocked epic issues and reopen anything whose dependencies are closed.