aw-ecc 1.4.21

package/scripts/uninstall.js

@@ -0,0 +1,96 @@
+#!/usr/bin/env node
+
+const { uninstallInstalledStates } = require('./lib/install-lifecycle');
+const { SUPPORTED_INSTALL_TARGETS } = require('./lib/install-manifests');
+
+function showHelp(exitCode = 0) {
+  console.log(`
+Usage: node scripts/uninstall.js [--target <${SUPPORTED_INSTALL_TARGETS.join('|')}>] [--dry-run] [--json]
+
+Remove ECC-managed files recorded in install-state for the current context.
+`);
+  process.exit(exitCode);
+}
+
+function parseArgs(argv) {
+  const args = argv.slice(2);
+  const parsed = {
+    targets: [],
+    dryRun: false,
+    json: false,
+    help: false,
+  };
+
+  for (let index = 0; index < args.length; index += 1) {
+    const arg = args[index];
+
+    if (arg === '--target') {
+      parsed.targets.push(args[index + 1] || null);
+      index += 1;
+    } else if (arg === '--dry-run') {
+      parsed.dryRun = true;
+    } else if (arg === '--json') {
+      parsed.json = true;
+    } else if (arg === '--help' || arg === '-h') {
+      parsed.help = true;
+    } else {
+      throw new Error(`Unknown argument: ${arg}`);
+    }
+  }
+
+  return parsed;
+}
+
+function printHuman(result) {
+  if (result.results.length === 0) {
+    console.log('No ECC install-state files found for the current home/project context.');
+    return;
+  }
+
+  console.log('Uninstall summary:\n');
+  for (const entry of result.results) {
+    console.log(`- ${entry.adapter.id}`);
+    console.log(`  Status: ${entry.status.toUpperCase()}`);
+    console.log(`  Install-state: ${entry.installStatePath}`);
+
+    if (entry.error) {
+      console.log(`  Error: ${entry.error}`);
+      continue;
+    }
+
+    const paths = result.dryRun ? entry.plannedRemovals : entry.removedPaths;
+    console.log(`  ${result.dryRun ? 'Planned removals' : 'Removed paths'}: ${paths.length}`);
+  }
+
+  console.log(`\nSummary: checked=${result.summary.checkedCount}, ${result.dryRun ? 'planned' : 'uninstalled'}=${result.dryRun ? result.summary.plannedRemovalCount : result.summary.uninstalledCount}, errors=${result.summary.errorCount}`);
+}
+
+function main() {
+  try {
+    const options = parseArgs(process.argv);
+    if (options.help) {
+      showHelp(0);
+    }
+
+    const result = uninstallInstalledStates({
+      homeDir: process.env.HOME,
+      projectRoot: process.cwd(),
+      targets: options.targets,
+      dryRun: options.dryRun,
+    });
+    const hasErrors = result.summary.errorCount > 0;
+
+    if (options.json) {
+      console.log(JSON.stringify(result, null, 2));
+    } else {
+      printHuman(result);
+    }
+
+    process.exitCode = hasErrors ? 1 : 0;
+  } catch (error) {
+    console.error(`Error: ${error.message}`);
+    process.exit(1);
+  }
+}
+
+main();

package/skills/agent-eval/SKILL.md

@@ -0,0 +1,145 @@
+---
+name: agent-eval
+description: Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
+origin: ECC
+tools: Read, Write, Edit, Bash, Grep, Glob
+---
+
+# Agent Eval Skill
+
+A lightweight CLI tool for comparing coding agents head-to-head on reproducible tasks. Every "which coding agent is best?" comparison runs on vibes — this tool systematizes it.
+
+## When to Activate
+
+- Comparing coding agents (Claude Code, Aider, Codex, etc.) on your own codebase
+- Measuring agent performance before adopting a new tool or model
+- Running regression checks when an agent updates its model or tooling
+- Producing data-backed agent selection decisions for a team
+
+## Installation
+
+> **Note:** Install agent-eval from its repository after reviewing the source.
+
+## Core Concepts
+
+### YAML Task Definitions
+
+Define tasks declaratively. Each task specifies what to do, which files to touch, and how to judge success:
+
+```yaml
+name: add-retry-logic
+description: Add exponential backoff retry to the HTTP client
+repo: ./my-project
+files:
+  - src/http_client.py
+prompt: |
+  Add retry logic with exponential backoff to all HTTP requests.
+  Max 3 retries. Initial delay 1s, max delay 30s.
+judge:
+  - type: pytest
+    command: pytest tests/test_http_client.py -v
+  - type: grep
+    pattern: "exponential_backoff|retry"
+    files: src/http_client.py
+commit: "abc1234"  # pin to specific commit for reproducibility
+```
+
+### Git Worktree Isolation
+
+Each agent run gets its own git worktree — no Docker required. This provides reproducibility isolation so agents cannot interfere with each other or corrupt the base repo.
+
+### Metrics Collected
+
+| Metric | What It Measures |
+|--------|-----------------|
+| Pass rate | Did the agent produce code that passes the judge? |
+| Cost | API spend per task (when available) |
+| Time | Wall-clock seconds to completion |
+| Consistency | Pass rate across repeated runs (e.g., 3/3 = 100%) |
+
+## Workflow
+
+### 1. Define Tasks
+
+Create a `tasks/` directory with YAML files, one per task:
+
+```bash
+mkdir tasks
+# Write task definitions (see template above)
+```
+
+### 2. Run Agents
+
+Execute agents against your tasks:
+
+```bash
+agent-eval run --task tasks/add-retry-logic.yaml --agent claude-code --agent aider --runs 3
+```
+
+Each run:
+1. Creates a fresh git worktree from the specified commit
+2. Hands the prompt to the agent
+3. Runs the judge criteria
+4. Records pass/fail, cost, and time
+
+### 3. Compare Results
+
+Generate a comparison report:
+
+```bash
+agent-eval report --format table
+```
+
+```
+Task: add-retry-logic (3 runs each)
+┌──────────────┬───────────┬────────┬────────┬─────────────┐
+│ Agent        │ Pass Rate │ Cost   │ Time   │ Consistency │
+├──────────────┼───────────┼────────┼────────┼─────────────┤
+│ claude-code  │ 3/3       │ $0.12  │ 45s    │ 100%        │
+│ aider        │ 2/3       │ $0.08  │ 38s    │  67%        │
+└──────────────┴───────────┴────────┴────────┴─────────────┘
+```
+
+## Judge Types
+
+### Code-Based (deterministic)
+
+```yaml
+judge:
+  - type: pytest
+    command: pytest tests/ -v
+  - type: command
+    command: npm run build
+```
+
+### Pattern-Based
+
+```yaml
+judge:
+  - type: grep
+    pattern: "class.*Retry"
+    files: src/**/*.py
+```
+
+### Model-Based (LLM-as-judge)
+
+```yaml
+judge:
+  - type: llm
+    prompt: |
+      Does this implementation correctly handle exponential backoff?
+      Check for: max retries, increasing delays, jitter.
+```
+
+## Best Practices
+
+- **Start with 3-5 tasks** that represent your real workload, not toy examples
+- **Run at least 3 trials** per agent to capture variance — agents are non-deterministic
+- **Pin the commit** in your task YAML so results are reproducible across days/weeks
+- **Include at least one deterministic judge** (tests, build) per task — LLM judges add noise
+- **Track cost alongside pass rate** — a 95% agent at 10x the cost may not be the right choice
+- **Version your task definitions** — they are test fixtures, treat them as code
+
+## Links
+
+- Repository: [github.com/joaquinhuigomez/agent-eval](https://github.com/joaquinhuigomez/agent-eval)

package/skills/agent-harness-construction/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: agent-harness-construction
+description: Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
+origin: ECC
+---
+
+# Agent Harness Construction
+
+Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion.
+
+## Core Model
+
+Agent output quality is constrained by:
+1. Action space quality
+2. Observation quality
+3. Recovery quality
+4. Context budget quality
+
+## Action Space Design
+
+1. Use stable, explicit tool names.
+2. Keep inputs schema-first and narrow.
+3. Return deterministic output shapes.
+4. Avoid catch-all tools unless isolation is impossible.
+
+## Granularity Rules
+
+- Use micro-tools for high-risk operations (deploy, migration, permissions).
+- Use medium tools for common edit/read/search loops.
+- Use macro-tools only when round-trip overhead is the dominant cost.
+
+## Observation Design
+
+Every tool response should include:
+- `status`: success|warning|error
+- `summary`: one-line result
+- `next_actions`: actionable follow-ups
+- `artifacts`: file paths / IDs
+
+## Error Recovery Contract
+
+For every error path, include:
+- root cause hint
+- safe retry instruction
+- explicit stop condition
+
+## Context Budgeting
+
+1. Keep system prompt minimal and invariant.
+2. Move large guidance into skills loaded on demand.
+3. Prefer references to files over inlining long documents.
+4. Compact at phase boundaries, not arbitrary token thresholds.
+
+## Architecture Pattern Guidance
+
+- ReAct: best for exploratory tasks with uncertain path.
+- Function-calling: best for structured deterministic flows.
+- Hybrid (recommended): ReAct planning + typed tool execution.
+
+## Benchmarking
+
+Track:
+- completion rate
+- retries per task
+- pass@1 and pass@3
+- cost per successful task
+
+## Anti-Patterns
+
+- Too many tools with overlapping semantics.
+- Opaque tool output with no recovery hints.
+- Error-only output without next steps.
+- Context overloading with irrelevant references.

package/skills/agentic-engineering/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: agentic-engineering
+description: Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
+origin: ECC
+---
+
+# Agentic Engineering
+
+Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.
+
+## Operating Principles
+
+1. Define completion criteria before execution.
+2. Decompose work into agent-sized units.
+3. Route model tiers by task complexity.
+4. Measure with evals and regression checks.
+
+## Eval-First Loop
+
+1. Define capability eval and regression eval.
+2. Run baseline and capture failure signatures.
+3. Execute implementation.
+4. Re-run evals and compare deltas.
+
+## Task Decomposition
+
+Apply the 15-minute unit rule:
+- each unit should be independently verifiable
+- each unit should have a single dominant risk
+- each unit should expose a clear done condition
+
+## Model Routing
+
+- Haiku: classification, boilerplate transforms, narrow edits
+- Sonnet: implementation and refactors
+- Opus: architecture, root-cause analysis, multi-file invariants
+
+## Session Strategy
+
+- Continue session for closely-coupled units.
+- Start fresh session after major phase transitions.
+- Compact after milestone completion, not during active debugging.
+
+## Review Focus for AI-Generated Code
+
+Prioritize:
+- invariants and edge cases
+- error boundaries
+- security and auth assumptions
+- hidden coupling and rollout risk
+
+Do not waste review cycles on style-only disagreements when automated format/lint already enforce style.
+
+## Cost Discipline
+
+Track per task:
+- model
+- token estimate
+- retries
+- wall-clock time
+- success/failure
+
+Escalate model tier only when lower tier fails with a clear reasoning gap.

package/skills/ai-first-engineering/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: ai-first-engineering
+description: Engineering operating model for teams where AI agents generate a large share of implementation output.
+origin: ECC
+---
+
+# AI-First Engineering
+
+Use this skill when designing process, reviews, and architecture for teams shipping with AI-assisted code generation.
+
+## Process Shifts
+
+1. Planning quality matters more than typing speed.
+2. Eval coverage matters more than anecdotal confidence.
+3. Review focus shifts from syntax to system behavior.
+
+## Architecture Requirements
+
+Prefer architectures that are agent-friendly:
+- explicit boundaries
+- stable contracts
+- typed interfaces
+- deterministic tests
+
+Avoid implicit behavior spread across hidden conventions.
+
+## Code Review in AI-First Teams
+
+Review for:
+- behavior regressions
+- security assumptions
+- data integrity
+- failure handling
+- rollout safety
+
+Minimize time spent on style issues already covered by automation.
+
+## Hiring and Evaluation Signals
+
+Strong AI-first engineers:
+- decompose ambiguous work cleanly
+- define measurable acceptance criteria
+- produce high-signal prompts and evals
+- enforce risk controls under delivery pressure
+
+## Testing Standard
+
+Raise testing bar for generated code:
+- required regression coverage for touched domains
+- explicit edge-case assertions
+- integration checks for interface boundaries