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 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.00159 | $0.02770 |
| Opus 5.5 | $0.00064 | $0.01108 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (7 stars, last pushed 21d ago), licensed MIT. It adds 159 tokens to every session and 2,770 once invoked, about $0.0006 per session on Opus 5.5. 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
honcho-cli
Inspect and debug Honcho workspaces via the honcho CLI. Use when investigating peer representations, memory state, session context, or dialectic quality — any task that requires introspection of a Honcho deployment, including verifying that a recall/record memory loop is actually working.
diagnose
Use when an AI Brain vault needs a health check or something feels off: Claude ignores CLAUDE.md, journal entries missing from /weekly, hooks not firing, something broke after a git pull, a friend's install misbehaves, Obsidian crashes or pegs the CPU, a .claude/worktrees folder appeared, Granola/WhatsApp/Slack/Gmail…
mem9
Persistent cloud memory for OpenClaw agents. Use when users say: "install mem9" "setup memory" "add memory plugin" "openclaw memory" "mem9 onboarding" "memory not working" "import memories" "upload sessions".
mem9
Persistent cloud memory for OpenClaw agents. Use when users say: "install mem9" "setup memory" "add memory plugin" "openclaw memory" "mem9 onboarding" "memory not working" "import memories" "upload sessions".
ultramemory-snapshot
Compose and save a durable, wayback-grade session snapshot to UltraMemory. Use this whenever you are asked to write a session snapshot or rollup of the work just done — in particular when the UltraMemory capture hook nudges you to "Compose a session snapshot per the ultramemory-snapshot Skill rubric ... and save it…
setup
Guides Claude through first-time UltraMemory configuration after plugin install — API key, MCP server registration, test recall, and 401/403 troubleshooting.