Development
Skill
/debug-memory
Query and manage the executable feedback debug memory
Claude Code
$ npx -y skills add jmagly/aiwg --skill debug-memory --agent claude-code
Codex
$ npx skills add jmagly/aiwg --skill debug-memory -a codex -y
Cursor
$ npx skills add jmagly/aiwg --skill debug-memory -a cursor -y
Gemini CLI
$ npx skills add jmagly/aiwg --skill debug-memory -a gemini-cli -y
GitHub Copilot
$ npx skills add jmagly/aiwg --skill debug-memory -a github-copilot -y
OpenCode
$ npx skills add jmagly/aiwg --skill debug-memory -a opencode -y
Windsurf
$ npx skills add jmagly/aiwg --skill debug-memory -a windsurf -y
SKILL.md
debug-memory.SKILL.mdnamespace: aiwg
name: debug-memory
platforms: [all]
description: Query and manage the executable feedback debug memory
commandHint:
category: code-quality
Debug Memory Command
Query, analyze, and manage the debug memory from executable feedback loops.
HITL authorization checkpoints
Before any confirmation below, read and apply [agent-loop authorization checkpoints](../../docs/hitl-authorization.md). Call `aiwg config authorization check --action-file "$ACTION_FILE" --target "$TARGET_REPO"` for host-classified effects. Only `auto-authorized` with a signed receipt skips that workflow prompt; retain existing prompts/refusals otherwise. Platform prompts are never bypassed. Limits, regression and threat overrides still require review.
Instructions
Manage the debug memory stored in `.aiwg/ralph/debug-memory/`:
Subcommand: query
Search debug memory for relevant past execution sessions.
1. Search `.aiwg/ralph/debug-memory/sessions/` for matching entries 2. Match by file path, error type, test name, or keyword 3. Display relevant sessions with fix attempts and outcomes 4. Highlight reusable patterns
Subcommand: patterns
Display learned patterns from past debug sessions.
1. Load `.aiwg/ralph/debug-memory/patterns/learned-patterns.yaml` 2. Show pattern frequency, success rate, and applicability 3. Suggest patterns applicable to current context
Subcommand: stats
Show aggregate statistics from debug memory.
1. Total sessions, pass rate, average attempts 2. Most common error types 3. Most effective fix patterns 4. Files with highest failure frequency
Subcommand: clear
Clear debug memory (with confirmation).
1. Prompt for confirmation 2. Archive current memory to `.aiwg/ralph/debug-memory/archive/` 3. Reset sessions and patterns
Arguments
- `query [keyword]` - Search debug memory
- `patterns` - Show learned patterns
- `stats` - Show aggregate statistics
- `clear` - Clear and archive debug memory
- `--file [path]` - Filter by source file
- `--error [type]` - Filter by error type
- `--since [date]` - Filter by date
References
- @$AIWG_ROOT/agentic/code/addons/agent-loop/schemas/debug-memory.yaml - Debug memory schema
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/executable-feedback.md - Executable feedback rules
- @$AIWG_ROOT/agentic/code/addons/agent-loop/docs/executable-feedback-guide.md - Guide
Read more
namespace: aiwg name: debug-memory platforms: [all] description: Query and manage the executable feedback debug memory commandHint: category: code-quality
Debug Memory Command
Query, analyze, and manage the debug memory from executable feedback loops.
HITL authorization checkpoints
Before any confirmation below, read and apply [agent-loop authorization checkpoints](../../docs/hitl-authorization.md). Call `aiwg config authorization check --action-file "$ACTION_FILE" --target "$TARGET_REPO"` for host-classified effects. Only `auto-authorized` with a signed receipt skips that workflow prompt; retain existing prompts/refusals otherwise. Platform prompts are never bypassed. Limits, regression and threat overrides still require review.
Instructions
Manage the debug memory stored in `.aiwg/ralph/debug-memory/`:
Subcommand: query
Search debug memory for relevant past execution sessions.
1. Search `.aiwg/ralph/debug-memory/sessions/` for matching entries 2. Match by file path, error type, test name, or keyword 3. Display relevant sessions with fix attempts and outcomes 4. Highlight reusable patterns
Subcommand: patterns
Display learned patterns from past debug sessions.
1. Load `.aiwg/ralph/debug-memory/patterns/learned-patterns.yaml` 2. Show pattern frequency, success rate, and applicability 3. Suggest patterns applicable to current context
Subcommand: stats
Show aggregate statistics from debug memory.
1. Total sessions, pass rate, average attempts 2. Most common error types 3. Most effective fix patterns 4. Files with highest failure frequency
Subcommand: clear
Clear debug memory (with confirmation).
1. Prompt for confirmation 2. Archive current memory to `.aiwg/ralph/debug-memory/archive/` 3. Reset sessions and patterns
Arguments
- `query [keyword]` - Search debug memory
- `patterns` - Show learned patterns
- `stats` - Show aggregate statistics
- `clear` - Clear and archive debug memory
- `--file [path]` - Filter by source file
- `--error [type]` - Filter by error type
- `--since [date]` - Filter by date
References
- @$AIWG_ROOT/agentic/code/addons/agent-loop/schemas/debug-memory.yaml - Debug memory schema
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/executable-feedback.md - Executable feedback rules
- @$AIWG_ROOT/agentic/code/addons/agent-loop/docs/executable-feedback-guide.md - Guide
Stats
229
Stars
36
Forks
Active
Maintenance
TypeScript
Language
MIT
License
Last commit
Created
Ships withaiwg
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
227200 skills199 agents
Stars on GitHub
Momentum
- stars in total
- 227
Other skills on aiwg.
More skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about debug-memory.
- Which coding agents can use debug-memory?
- debug-memory installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.