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/jinning6/noosphere/agent-debug-memorynpx skills add JinNing6/Noosphere --skill agent-debug-memorygit clone --depth 1 https://github.com/JinNing6/NoosphereWhat 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 | $0.00050 | $0.00510 |
| Opus 5 | $0.00025 | $0.00255 |
| Sonnet 5 | $0.00010 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
agent-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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Debug Memory
Use Noosphere as the shared debugging memory layer before and after substantial debugging work.
Before Fixing
- Extract a precise query from the failure:
- exact error text, stack frame, failing command, failing test, or visible symptom
- framework, package, runtime, OS, database, browser, or deployment context
- the user's concrete goal and any constraints already stated
- Call the Noosphere MCP tool
consult_noospherewith that query. - If useful tags are obvious, include focused
topic_tags, such asreact,vite,typescript,mcp,github-actions,async-ui,codex,claude-code,windows, or the library name. - Treat returned fragments as leads, not truth. Verify against the local codebase, official docs when needed, and runnable tests or reproduction steps.
During Fixing
- Prefer the smallest complete fix that addresses the verified root cause.
- Do not copy a Noosphere fragment blindly if the local environment, version, lifecycle, or data flow differs.
- Keep secrets, tokens, private customer data, private code snippets, and credentials out of tool calls and uploaded memories.
After Fixing
When the outcome is verified, the lesson is reusable, and the user explicitly approves the external GitHub write, upload a distilled memory with upload_consciousness.
Use:
consciousness_type: "warning"for pitfalls, footguns, version traps, and failure modes.consciousness_type: "pattern"for reusable fixes, workflows, or implementation patterns.consciousness_type: "decision"for tradeoff-heavy engineering choices.
The uploaded memory should include:
- the symptom or failing command
- the root cause
- the fix
- the verification command or evidence
- version or environment details that prevent false reuse
Keep the memory concise and general enough for another agent to reuse.
Completion Standard
Do not claim the fix is complete until local verification has passed or you have clearly stated what could not be run. Public registry reads work anonymously; uploading evidence or outcomes requires a GitHub token in the Agent's Noosphere MCP environment.
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 · 49 lines · 50 tokens per session scan A d15ebefd3fa2
agent-debug-memory is a skill published in the GitHub repository JinNing6/Noosphere (18 stars, last pushed 9d ago), licensed Apache-2.0. It adds 50 tokens to every session and 510 once invoked, about $0.0003 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
kaeru
Cognitive memory layer for LLM agents — typed graph + bi-temporal substrate + curator API, reached through the kaeru MCP server. Use when the user wants to capture, recall, reason, or trace persistent thoughts across sessions; when re-entering a multi-session project; or when the user explicitly asks to "remember"…
generating-mod-envs
Generates and reviews mod learning env JSON files for Letta Code local mods. Use when asked to teach, learn, or optimize a mod behavior; create, draft, validate, improve, or explain envs for /mods learn --env; or design evaluation scenarios, memory fixtures, requiredResultMarkers, requiredTraceMarkers, negative…
run-history-skill-builder
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons…
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…
memory-curation
When you have read / processed a workspace asset in this session and learned something durable about it, write a memory page so future sessions benefit. Maintain the workspace wiki's hierarchical structure as it grows.
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.