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/upload-debug-memorynpx skills add JinNing6/Noosphere --skill upload-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 | $0.00041 | $0.00575 |
| Opus 5 | $0.00020 | $0.00287 |
| Sonnet 5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
upload-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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submit Debug Skill Evidence
Submit reusable, verified debugging lessons to the Noosphere Shared Skill lifecycle. Engineering evidence must not be uploaded as a consciousness fragment.
Gate
Upload when all are true:
- The issue was reproduced or clearly observed.
- The root cause is known.
- The fix or workaround was verified.
- The lesson is likely to help another agent avoid wasted debugging time.
- The user has explicitly approved the external GitHub write.
Do not upload:
- secrets, tokens, private data, customer data, proprietary source snippets, or credentials
- speculation that was not verified
- one-off local machine state with no reusable lesson
- full logs when a concise symptom and root cause are enough
Shape
Call submit_skill_evidence only after the user approves this specific public write:
skill_name: a proposed lowercase kebab-case name, or an existing registry Skill name.symptom,root_cause,fix,verification,applies_when, and optionalavoid_when.test_commands: real commands that another Agent can rerun.source_urls: optional public upstream Issues, PRs, or artifacts. If omitted, the created public evidence Issue becomes the canonical source record.tags: focused tags for framework, tool, OS, language, and failure class.publication_track:communityby default. Usemaintaineronly when an authenticated repository maintainer explicitly chooses it.
Never call upload_consciousness for a software engineering fix. That tool is reserved
for general thoughts and philosophical consciousness fragments.
Recommended Memory Template
Symptom: <exact user-visible failure>
Root cause: <verified mechanism>
Fix: <minimal complete fix>
Verification: <command, test, screenshot, or observed result>
Applies when: <versions, framework, OS, lifecycle, data shape>
Avoid when: <known non-applicable cases>
Lifecycle Result
Report the returned state exactly:
evidence-recordedmeans the public evidence exists, but it is not callable.- Community evidence still needs a matching independent publisher and shared command.
- Maintainer evidence still needs a separate trusted review and can only publish as
maintainer-validated. - Only a reviewed immutable registry release is a callable Shared Skill.
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 · 68 lines · 41 tokens per session scan A 557c39266813
upload-debug-memory is a skill published in the GitHub repository JinNing6/Noosphere (18 stars, last pushed 9d ago), licensed Apache-2.0. It adds 41 tokens to every session and 575 once invoked, about $0.0002 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.