alebgl77/tierdecay
Per-repo learning layer for AI coding model routers: learns which task classes can safely run on a cheaper tier. Native for Claude Code, Codex, Antigravity · MCP server · zero deps.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add tierdecay -- tierdecay mcp $ npx degit alebgl77/tierdecay/adapters/claude-code/.claude ./rig-tierdecay # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add tierdecay -- tierdecay mcp $ npx degit alebgl77/tierdecay/adapters/claude-code/.claude/skills/execution-standards .claude/skills/execution-standards $ npx degit alebgl77/tierdecay/adapters/claude-code/.claude/skills/model-routing .claude/skills/model-routing $ npx degit alebgl77/tierdecay/adapters/claude-code/.claude/skills/repo-playbook .claude/skills/repo-playbook $ npx degit alebgl77/tierdecay/adapters/claude-code/.claude/skills/tier-decay .claude/skills/tier-decay $ npx degit <redacted> .claude/skills/init
$ curl -fsSL --create-dirs -o .claude/agents/executor.md https://raw.githubusercontent.com/alebgl77/tierdecay/main/adapters/claude-code/.claude/agents/executor.md $ curl -fsSL --create-dirs -o .claude/agents/heavy-executor.md https://raw.githubusercontent.com/alebgl77/tierdecay/main/adapters/claude-code/.claude/agents/heavy-executor.md $ curl -fsSL --create-dirs -o .claude/agents/oracle.md https://raw.githubusercontent.com/alebgl77/tierdecay/main/adapters/claude-code/.claude/agents/oracle.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/alebgl77/tierdecay/main/adapters/claude-code/.claude/agents/scout.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"ask": [
"Edit(.claude/**)",
"Edit(.tierdecay/**)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| tierdecay | binary | 2.5k |
Skills (5)
Subagents (4)
| executor model: sonnet | Standard implementation agent for well-specified tasks tagged [T1] — features from a clear spec, unit tests, documentation, renames, config changes, mechanical multi-file edits, straightforward bugfix |
| heavy-executor model: opus | Complex implementation agent for tasks tagged [T2] — multi-file refactors, concurrency/async, schema and data migrations, performance optimization, intricate state machines, bugs with unclear repro, s |
| oracle model: opus | Highest-reasoning tier, read-only. Use for (a) REVIEW of critical diffs — security, auth, payments, data migrations, public API contracts; (b) SOLVE — designing novel algorithms or root-causing bugs t |
| scout model: sonnet | Read-only codebase reconnaissance. Use PROACTIVELY before any planning or implementation to map relevant files, symbols, data flow, conventions, and risks. Never writes or modifies anything. |
Permissions
deny (0)
—
ask (2)
Edit(.claude/**)
Edit(.tierdecay/**)
allow (0)
—
Similar rigs
bentleypark/claude-code-mobile-spine
Claude Code plugin marketplace bundling mobile-spine — scaffolds a meta-repo coordinating 4 subagents (api/pm/android/ios) for mobile teams whose Android, iOS, and Backend live in 3 separate repos.
Minimalist 84 tok ·
yongkyung-oh/agent-bootstrap
A minimal workflow bootstrap for AI coding agents — three markdown files that solve context loss between sessions. No framework, no dependencies.
Minimalist 1.7k tok ·
leavemagic-cyber/earned-confidence
A behavior contract for AI coding agents — every rule added after a real failure. Ships with a verifier agent that cannot edit what it judges.
Pragmatist 3.6k tok ·
oter/bruh
Claude Code plugin for coordinating work across sessions and machines: coordinator, clankers, clerks, workflows
Pragmatist 5.2k tok ·