kromahlusenii-ops/ham / ham
ham
VerifiedSet up and maintain Hierarchical Agent Memory (HAM) for Codex using scoped local memory files. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "HAM audit".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.6 KB |
| agents/openai.yaml | config | 181 B |
| references/platforms.md | markdown | 1.1 KB |
| references/setup-and-scopes.md | markdown | 2.2 KB |
| references/templates.md | markdown | 1.8 KB |
references/templates.md
View on GitHub# Templates
Use these starter shapes when creating HAM files. Keep them short and adapt them to the actual repo.
## Root CLAUDE.md
```markdown
# Project: [Name]
## Stack
- Framework: [framework]
- Language: [language]
- Database: [database]
- Testing: [test stack]
## Critical Rules
- [global rule]
- [global rule]
## Agent Memory System
### Before Working
- Read this file for global context, then read the target directory's CLAUDE.md before changes
- If this file has a ## Context Routing section, use it to find the right scoped CLAUDE.md
- Check .memory/decisions.md before architectural changes
- Check .memory/patterns.md before implementing common functionality
### During Work
- Create CLAUDE.md in any new directory that needs distinct guidance
### After Work
- Update relevant CLAUDE.md if conventions changed
- Log decisions to .memory/decisions.md
- Log patterns to .memory/patterns.md
- Put uncertain inferences in .memory/inbox.md
### Safety
- Never record secrets, API keys, or user data
- Never overwrite decisions; mark them superseded
- Never promote from inbox without user confirmation
```
## Scoped CLAUDE.md
```markdown
# [Directory] Context
## Purpose
[One sentence]
## Conventions
- [local rule]
## Active Integrations
- [integration]: [note]
## Key Patterns
- [pattern]: [note]
## Gotchas
- [non-obvious warning]
```
## decisions.md
```markdown
### [Decision Title]
- **Status**: accepted
- **Date**: YYYY-MM-DD
- **Context**: [why the choice mattered]
- **Decision**: [chosen approach]
- **Alternatives**: [other options considered]
```
## patterns.md
```markdown
### [Pattern Title]
- **When**: [when to apply it]
- **Do**: [recommended implementation]
- **Don't**: [what to avoid]
```
## inbox.md
```markdown
# Inbox
Use this file for uncertain observations that still need review.
- [YYYY-MM-DD] [observation]
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |