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 NulightJens/ai-second-brain-skills --skill wiki-self-healgit clone --depth 1 https://github.com/NulightJens/ai-second-brain-skillsWrote 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/nulightjens/ai-second-brain-skills/wiki-self-heal)<a href="https://agentmods.dev/skills/nulightjens/ai-second-brain-skills/wiki-self-heal"><img src="https://agentmods.dev/badge/skills/nulightjens/ai-second-brain-skills/wiki-self-heal/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/nulightjens/ai-second-brain-skills/wiki-self-heal"><img src="https://agentmods.dev/badge/skills/nulightjens/ai-second-brain-skills/wiki-self-heal.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 | $0.00142 | $0.02097 |
| Opus 5 | $0.00071 | $0.01048 |
| Sonnet 5 | $0.00028 | $0.00419 |
| Haiku 4.5 | $0.00014 | $0.00210 |
Grade A, and why
wiki-self-heal 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 12d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-self-heal
Audit → research → fill → commit. An autonomous pass over a Karpathy-style LLM wiki that finds what's weak or missing, researches high-quality answers, writes them into the wiki, and commits to a dedicated branch for human review.
Inspired by Karpathy's autoresearch loop: isolated branch per run, explicit CAN/CANNOT rules, numbered steps, structured logging, simplicity criterion, and a NEVER STOP autonomy directive once the loop begins.
When to use
User says: "lint my wiki", "self-heal", "find gaps", "auto-research my wiki", "update my second brain", "health check my wiki", "audit my wiki" or "dry run" (audit-only mode), or has scheduled this skill via cron / GitHub Actions / Claude Code triggers.
Two modes
- Full mode (default) — audit → research → apply → commit. Changes the wiki on a heal branch.
- Audit-only mode — audit → report. No research, no changes to wiki pages. The audit report itself is still committed to the branch.
Infer the mode from phrasing. If the user says "dry run", "just audit", "audit only", "don't make changes", or "show me the gaps first" → audit-only. If the user just says "lint" or "self-heal" → full mode. If unsure, ask once.
Preconditions
Before doing anything:
- The vault has Karpathy wiki structure:
raw/,wiki/,CLAUDE.md,wiki/index.md,wiki/log.md. If any are missing → stop and suggest running thellm-wiki-setupskill first. - The vault is a git repo. If not →
git init && git add . && git commit -m "chore: pre-heal snapshot"before continuing. - The git working tree is clean. If dirty → stop and ask the user to commit or stash first.
Research tool selection
At the start of the first run in a session, ask once:
I'll default to WebSearch + WebFetch for research. If you have any of these MCPs installed for higher-quality sources, let me know which and I'll prefer them: Apify, Firecrawl, Exa.
Priority order when available: Exa → Firecrawl → Apify → WebSearch/WebFetch. Fall back to the next tool on any failure. Never block the loop on tool selection — WebSearch + WebFetch always work.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 156 lines · 142 tokens per session scan A b3da24a6448f
wiki-self-heal is a skill published in the GitHub repository NulightJens/ai-second-brain-skills (97 stars, last pushed 5mo ago), licensed MIT. It adds 142 tokens to every session and 2,097 once invoked, about $0.0007 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.