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/lh8ppl/core-memory-kit/troubleshootingnpx skills add LH8PPL/core-memory-kit --skill troubleshootinggit clone --depth 1 https://github.com/LH8PPL/core-memory-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lh8ppl/core-memory-kit/troubleshooting)<a href="https://agentmods.dev/skills/lh8ppl/core-memory-kit/troubleshooting"><img src="https://agentmods.dev/badge/skills/lh8ppl/core-memory-kit/troubleshooting.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00159 | $0.02770 |
| Opus 5 | $0.00079 | $0.01385 |
| Sonnet 5 | $0.00032 | $0.00554 |
| Haiku 4.5 | $0.00016 | $0.00277 |
Grade A, and why
troubleshooting 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 4d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repairing the memory kit
Something in core-memory-kit is failing. Diagnose it, then repair what you are allowed to repair and PROPOSE the rest.
The one rule that outranks everything below
Never run a fix that touches the user's own state without asking first.
Each failure code below carries a fix class, and it is binding:
| Fix class | What you may do |
|---|---|
| silent | Just run it. Kit-owned, idempotent, reversible — it rebuilds a derived view and destroys nothing. Say afterwards what you ran, in one line. |
| confirm | Prepare the exact command, show it, and wait for the user to approve before running it. Anything that rewrites memory content, settings, or install state is this class. |
| advise | Do not run it. Print the command and what it will do. This is for fixes that are expensive, or outside the kit's authority (installing someone's CLI, changing their PATH). |
When you are unsure which class a failure belongs to, treat it as advise. An unknown failure never earns silent repair.
This is enforced, not just asked for: the only repair commands granted to this
skill are cmk doctor, cmk reindex, and read-only lookups. cmk install
and every form of cmk repair are deliberately ungranted — where a section
below tells you to propose one, you propose it and the user runs it. If a
command you need is not available to you, that is the boundary working, not a
misconfiguration to route around.
The kit's memory tiers are only ever written through the kit's own commands. Never hand-edit a file under the memory directories to "fix" anything — that bypasses the safety screens and is itself a failure mode.
Step 1 — read the evidence before running anything
The whisper on the prompt already names the failure code. If you need more:
cmk doctor— the full health audit. Every check reports PASS / WARN / FAIL / SKIP with a repair command. This is the diagnosis, not the fix; doctor repairs nothing by itself.context/.locks/health.log— the kit's own append-only failure log, one JSON object per line:{ts, class, outcome, detail}. Read the tail. Afailfollowed by a laterokfor the same class means the problem already cleared.
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.
- 4d ago First seen · 228 lines · 159 tokens per session scan A 4ed3a6e35686
troubleshooting is a skill published in the GitHub repository LH8PPL/core-memory-kit (6 stars, last pushed 6d ago), licensed MIT. It adds 159 tokens to every session and 2,770 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
Effective Memory
The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.
emulo
Use when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history and native emulo:mine is not available. This is the cross-agent skills.sh bootstrap, not the native namespaced plugin.
plur-memory
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.
emulo
Load the user's Emulo profile, mined from their local Claude Code, Codex, and OpenCode session logs, so you work like them instead of a cold start. Use before working on their task.
mengram-memory
Long-term memory with 3 types (facts, events, workflows). Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, or tracking completed workflows.