Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add YoungjaeDev/my-claude-plugins/plugin install wikiWrote 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/youngjaedev/my-claude-plugins/bootstrap-wiki)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/bootstrap-wiki"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/bootstrap-wiki.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 5.1 | $0.00120 | $0.02317 |
| Opus 5 | $0.00060 | $0.01158 |
| Sonnet 5 | $0.00024 | $0.00463 |
| Haiku 4.5 | $0.00012 | $0.00232 |
Grade A, and why
bootstrap-wiki 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 today.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bootstrap-wiki
LLM-Wiki 3-layer = .llmwiki/insight/ (promoted cross-agent rules) + .llmwiki/wiki/ (LLM-maintained lore) + .llmwiki/raw/ (immutable evidence). This skill drops the empty layout into any repo so the per-PR workflow (spec → resolve-issue → post-merge → ingest) has a place to land. All three layers live under the neutral .llmwiki/ root so no per-agent transform can fork them: one copy, both agents (Claude Code + Codex). This skill does not scaffold a .claude/rules/ schema layer: Codex can't read it, so cross-agent rules graduate to .llmwiki/insight/ and reach both runtimes via the core prompt-injection hook instead. .claude/rules/ stays reserved for mechanical tool-operation rules (not wiki lore), which this skill leaves to the project.
Ships with
wikiplugin; install via marketplace. Templates bundled at<plugin-root>/skills/bootstrap-wiki/assets/templates/. Step 3 resolves<plugin-root>across runtimes (ClaudeCLAUDE_PLUGIN_ROOT, Codex plugin cache), since Codex 0.135 does not exportCLAUDE_PLUGIN_ROOT.
When to use
- Brand new repo with no
.claude/directory - Existing repo where
.claude/is justsettings.local.json(or missing) and you want to start LLM-Wiki discipline - Asking "how do I add the wiki system here?"
Do NOT scaffold if any of the three roots (.llmwiki/wiki/, .claude/wiki/, .codex/wiki/) is already populated (index.md/log.md are the usual signals, but Step 1's populated-root check is the authoritative guard): the wiki is already initialized; read index.md directly or use /wiki:ingest-finding. Migration mode (a "migrate wiki" / "upgrade wiki" request on a populated legacy root) runs the procedure in this paragraph instead of the Steps below. If only a legacy .claude/wiki/ (or .codex/wiki/) exists and you want the v2 .llmwiki/ layout, migrate manually: mkdir -p .llmwiki && mv <legacy-root> .llmwiki/wiki where <legacy-root> is whichever of .claude/wiki / .codex/wiki actually exists, add the v2 frontmatter fields (status/volatility/sources) opportunistically as pages get touched, then run /wiki:lint-wiki to surface gaps. The dedicated migrate-wiki skill was retired once the legacy-fork era ended. If BOTH legacy roots exist (a repo forked by the retired codex-bridge), do not mv either one: .llmwiki/wiki/ resolves first, so the pages unique to the root you did not move become invisible. Instead create .llmwiki/wiki/ empty, copy pages from both roots merging by frontmatter id (identical pages once, diverging bodies only after the user picks or reconciles them), and delete the two originals only after /wiki:lint-wiki passes on the merged tree.
What ships with it
6 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.
- today Changed · +51 tokens per session bd8de9219b9b
- 5d ago First seen · 91 lines · 69 tokens per session scan A b92cdcbe4af5
bootstrap-wiki is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 2,317 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…