Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jmagly/aiwg/debug-memorynpx skills add jmagly/aiwg --skill debug-memorygit clone --depth 1 https://github.com/jmagly/aiwgWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00011 | $0.00452 |
| Opus 5 | $0.00005 | $0.00226 |
| Sonnet 5 | $0.00002 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
debug-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Debug Memory Command
Query, analyze, and manage the debug memory from executable feedback loops.
Instructions
Manage the debug memory stored in .aiwg/ralph/debug-memory/:
Subcommand: query
Search debug memory for relevant past execution sessions.
- Search
.aiwg/ralph/debug-memory/sessions/for matching entries - Match by file path, error type, test name, or keyword
- Display relevant sessions with fix attempts and outcomes
- Highlight reusable patterns
Subcommand: patterns
Display learned patterns from past debug sessions.
- Load
.aiwg/ralph/debug-memory/patterns/learned-patterns.yaml - Show pattern frequency, success rate, and applicability
- Suggest patterns applicable to current context
Subcommand: stats
Show aggregate statistics from debug memory.
- Total sessions, pass rate, average attempts
- Most common error types
- Most effective fix patterns
- Files with highest failure frequency
Subcommand: clear
Clear debug memory (with confirmation).
- Prompt for confirmation
- Archive current memory to
.aiwg/ralph/debug-memory/archive/ - Reset sessions and patterns
Arguments
query [keyword]- Search debug memorypatterns- Show learned patternsstats- Show aggregate statisticsclear- 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/ralph/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/ralph/docs/executable-feedback-guide.md - Guide
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 67 lines · 11 tokens per session scan A 6cbe0b33f5ca
debug-memory is a skill published in the GitHub repository jmagly/aiwg (205 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 452 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
archive
File the finished part of the run state into a dated archive — shipped items, research, opportunities, the rotated journal, and handled snags. The live files stay lean; the facts stay on disk.
doctor
Read-only Nightshift diagnosis — workspace, rules, markers, session, process lease, watchman, deadline, and classified next actions. Use when a shift looks wrong, recovery is unclear, or the owner asks what Nightshift sees. Never repairs by being invoked.
import-issues
Stage explicitly selected GitHub issues onto the drafting table as quoted source. Never searches, never writes back to GitHub, never installs gh.
purge
Permanently delete this project's Nightshift state. Does not uninstall the plugin.
reset
Abandon current Nightshift runtime mechanics without deleting the owner's work or evidence.
stop
Issue a stop-work order — pause the shift immediately, leaving unfinished items open.