Leverage Point Audit

Audit a codebase for the 12 leverage points of agentic coding. Identifies gaps and provides prioritized recommendations. Use when improving agentic coding capability, analyzing why agents fail, or optimizing a codebase for autonomous work. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

Install

Press C to copy

$ npx get-skill add tomevault-io/leverage-point-audit

Installs into ~/.claude/skills (or .claude/skills inside a project). Restart Claude Code to pick it up.

＋ Add to plugin

README badge

[![SkillMD](https://skillmd.com/badge/tomevault-io/leverage-point-audit.svg)](https://skillmd.com/skills/tomevault-io/leverage-point-audit)

Trust & safety

3 of 3 audits passed

Last audited Sep 30, 2026 · commit 719bbe8

Works with: Claude Code Claude.ai OpenAI Codex +

File contents

Leverage Point Audit

Audit a codebase against the 12 leverage points framework to identify gaps and improve agentic coding success.

When to Use

Before starting a new agentic coding project
When agents are failing or requiring many attempts
When KPIs (Size, Attempts, Streak, Presence) are not improving
For periodic health checks of agentic capability

The 12 Leverage Points

In-Agent (Core Four)

Context - CLAUDE.md, README, project docs
Model - Appropriate model selection
Prompt - Clear instructions and templates
Tools - Required capabilities available

Through-Agent (External)

Standard Out - Logging for visibility
Types - Information Dense Keywords (IDKs)
Documentation - Agent-specific context
Tests - Self-correction capability (HIGHEST LEVERAGE)
Architecture - Navigable codebase structure
Plans - Meta-work communication
Templates - Reusable prompts (slash commands)
ADWs - Autonomous workflows

Audit Workflow

Step 1: Check Context (Leverage Points 1-4)

CLAUDE.md presence:

Search for: CLAUDE.md, .claude/CLAUDE.md
Check: Does it explain the project? Conventions? Common commands?

README.md quality:

Search for: README.md
Check: Does it explain structure? How to run? How to test?

Permissions configuration:

Search for: .claude/settings.json
Check: Are required tools allowed?

Step 2: Check Visibility (Leverage Point 5)

Standard out patterns:

Search for: print(, console.log(, logger., logging.
Check: Are success AND error cases logged?
Check: Can agent see what's happening?

Anti-pattern detection:

Look for: Silent returns, bare except blocks, empty catch blocks
These prevent agent visibility.

Step 3: Check Searchability (Leverage Point 6)

Type definitions:

Search for: interface, type, class, BaseModel, dataclass
Check: Are names information-dense? (Good: UserAuthToken, Bad: Data)

Step 4: Check Documentation (Leverage Point 7)

Internal docs:

Search for: *.md files, docstrings, comments
Check: Do they explain WHY, not just WHAT?

Step 5: Check Validation (Leverage Point 8) - HIGHEST PRIORITY

Test presence:

Search for: test_*.py, *.test.ts, *.spec.ts, *_test.go
Check: Do tests exist? Are they comprehensive?

Test commands:

Check: Is there a simple test command? (npm test, pytest, etc.)
Check: Do tests run quickly?

Step 6: Check Architecture (Leverage Point 9)

Entry points:

Check: Are entry points obvious? (main.py, index.ts, server.py)

File organization:

Check: Consistent structure? Related files grouped?
Check: File sizes reasonable? (< 1000 lines)

Step 7: Check Templates (Leverage Point 11)

Slash commands:

Search for: .claude/commands/
Check: Are common workflows automated?

Step 8: Check ADWs (Leverage Point 12)

Automation:

Search for: GitHub Actions, hooks, triggers
Check: Are workflows automated?

Output Format

After audit, provide:

Summary Table

Leverage Point	Status	Priority	Recommendation
Context	Good/Fair/Poor	High/Med/Low	Specific action
...	...	...	...

Priority Actions

List top 3-5 improvements in order of impact:

[Highest Impact] - Specific recommendation
[High Impact] - Specific recommendation
[Medium Impact] - Specific recommendation

Detailed Findings

For each leverage point:

Current state
Specific gaps found
Recommended improvements
Example of what good looks like

Example Audit Output

## Leverage Point Audit Results

### Summary
- Tests: POOR (no test files found) - HIGHEST PRIORITY
- Standard Out: FAIR (some logging, missing error cases)
- Architecture: GOOD (clear structure, reasonable file sizes)

### Priority Actions
1. Add test suite - enables self-correction
2. Add error logging to API endpoints - enables visibility
3. Create /prime command - enables quick context

### Detailed Findings
[... specific recommendations ...]

Related Memory Files

@12-leverage-points.md - Complete framework reference
@agentic-kpis.md - How to measure improvement
@agent-perspective-checklist.md - Quick pre-task checklist

Version History

v1.0.0 (2025-12-26): Initial release

Last Updated

Date: 2025-12-26 Model: claude-opus-4-5-20251101

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: leverage-point-auditdescription: Audit a codebase for the 12 leverage points of agentic coding. Identifies gaps and provides prioritized recommendations. Use when improving agentic coding capability, analyzing why agents fail, or optimizing a codebase for autonomous work. Use when this capability is needed.---# Leverage Point AuditAudit a codebase against the 12 leverage points framework to identify gaps and improve agentic coding success.## When to Use- Before starting a new agentic coding project- When agents are failing or requiring many attempts- When KPIs (Size, Attempts, Streak, Presence) are not improving- For periodic health checks of agentic capability## The 12 Leverage Points### In-Agent (Core Four)1. **Context** - CLAUDE.md, README, project docs2. **Model** - Appropriate model selection3. **Prompt** - Clear instructions and templates4. **Tools** - Required capabilities available### Through-Agent (External)1. **Standard Out** - Logging for visibility2. **Types** - Information Dense Keywords (IDKs)3. **Documentation** - Agent-specific context4. **Tests** - Self-correction capability (HIGHEST LEVERAGE)5. **Architecture** - Navigable codebase structure6. **Plans** - Meta-work communication7. **Templates** - Reusable prompts (slash commands)8. **ADWs** - Autonomous workflows## Audit Workflow### Step 1: Check Context (Leverage Points 1-4)**CLAUDE.md presence:**```yamlSearch for: CLAUDE.md, .claude/CLAUDE.mdCheck: Does it explain the project? Conventions? Common commands?```**README.md quality:**```yamlSearch for: README.mdCheck: Does it explain structure? How to run? How to test?```**Permissions configuration:**```yamlSearch for: .claude/settings.jsonCheck: Are required tools allowed?```### Step 2: Check Visibility (Leverage Point 5)**Standard out patterns:**```yamlSearch for: print(, console.log(, logger., logging.Check: Are success AND error cases logged?Check: Can agent see what's happening?```**Anti-pattern detection:**```textLook for: Silent returns, bare except blocks, empty catch blocksThese prevent agent visibility.```### Step 3: Check Searchability (Leverage Point 6)**Type definitions:**```yamlSearch for: interface, type, class, BaseModel, dataclassCheck: Are names information-dense? (Good: UserAuthToken, Bad: Data)```### Step 4: Check Documentation (Leverage Point 7)**Internal docs:**```yamlSearch for: *.md files, docstrings, commentsCheck: Do they explain WHY, not just WHAT?```### Step 5: Check Validation (Leverage Point 8) - HIGHEST PRIORITY**Test presence:**```yamlSearch for: test_*.py, *.test.ts, *.spec.ts, *_test.goCheck: Do tests exist? Are they comprehensive?```**Test commands:**```yamlCheck: Is there a simple test command? (npm test, pytest, etc.)Check: Do tests run quickly?```### Step 6: Check Architecture (Leverage Point 9)**Entry points:**```yamlCheck: Are entry points obvious? (main.py, index.ts, server.py)```**File organization:**```yamlCheck: Consistent structure? Related files grouped?Check: File sizes reasonable? (< 1000 lines)```### Step 7: Check Templates (Leverage Point 11)**Slash commands:**```yamlSearch for: .claude/commands/Check: Are common workflows automated?```### Step 8: Check ADWs (Leverage Point 12)**Automation:**```yamlSearch for: GitHub Actions, hooks, triggersCheck: Are workflows automated?```## Output FormatAfter audit, provide:### Summary Table| Leverage Point | Status | Priority | Recommendation || --- | --- | --- | --- || Context | Good/Fair/Poor | High/Med/Low | Specific action || ... | ... | ... | ... |### Priority ActionsList top 3-5 improvements in order of impact:1. **[Highest Impact]** - Specific recommendation2. **[High Impact]** - Specific recommendation3. **[Medium Impact]** - Specific recommendation### Detailed FindingsFor each leverage point:- Current state- Specific gaps found- Recommended improvements- Example of what good looks like## Example Audit Output```markdown## Leverage Point Audit Results### Summary- Tests: POOR (no test files found) - HIGHEST PRIORITY- Standard Out: FAIR (some logging, missing error cases)- Architecture: GOOD (clear structure, reasonable file sizes)### Priority Actions1. Add test suite - enables self-correction2. Add error logging to API endpoints - enables visibility3. Create /prime command - enables quick context### Detailed Findings[... specific recommendations ...]```## Related Memory Files- @12-leverage-points.md - Complete framework reference- @agentic-kpis.md - How to measure improvement- @agent-perspective-checklist.md - Quick pre-task checklist## Version History- **v1.0.0** (2025-12-26): Initial release---## Last Updated**Date:** 2025-12-26**Model:** claude-opus-4-5-20251101---> Converted and distributed by [TomeVault](https://tomevault.io/claim/melodic-software) — claim your Tome and manage your conversions.

tomevault-io/skills-registry/tree/main/melodic-software--claude-code-plugins--leverage-point-audit commit 719bbe8457

Frequently asked questions

npx get-skill add tomevault-io/leverage-point-audit