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 receptron/mulmoclaude --skill mc-wiki-promotegit clone --depth 1 https://github.com/receptron/mulmoclaudeWrote 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/receptron/mulmoclaude/mc-wiki-promote)<a href="https://agentmods.dev/skills/receptron/mulmoclaude/mc-wiki-promote"><img src="https://agentmods.dev/badge/skills/receptron/mulmoclaude/mc-wiki-promote/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/receptron/mulmoclaude/mc-wiki-promote"><img src="https://agentmods.dev/badge/skills/receptron/mulmoclaude/mc-wiki-promote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 104 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00112 | $0.01976 |
| Opus 5 | $0.00056 | $0.00988 |
| Sonnet 5 | $0.00022 | $0.00395 |
| Haiku 4.5 | $0.00011 | $0.00198 |
Grade A, and why
mc-wiki-promote 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Promote
A bundled MulmoClaude preset skill (mc- prefix = launcher-managed; do not edit
this file in the workspace, it is overwritten on every server boot).
This is the query→page return-loop of the LLM-Wiki pattern
(Karpathy's gist: "ask questions against wiki pages; file valuable
answers back as new pages"). Where mc-wiki-ingest (Phase A) starts
from an external source, this one starts from a Q&A in the
current chat: a question the user just asked plus the assistant's
just-given answer that's worth keeping. Writes to data/wiki/.
Sister presets:
mc-wiki-health-check(D, structural lint, scheduled, read-only)mc-wiki-deep-lint(B, LLM lint, on-demand, read-only)mc-wiki-ingest(A, source-driven ingest, writes)mc-wiki-promote(C, this one — chat-derived promote, writes)
Inputs
Reads from the current chat session — no file path / pasted text needed. The capture unit is:
- the assistant turn the user is promoting (their previous message in the case where the user invokes this skill right after a useful answer — i.e. the answer just spoken)
- the immediately prior user turn (the question that elicited it)
That's the Q&A pair (per #1528 Q2). If the prior user turn isn't a question — for example the user said "actually, also save this" after the assistant's answer — pair the assistant turn with the most recent user turn that does look like a question. If no usable question can be found, ask the user to restate the topic in one line and use that as the synthesised question.
Do NOT crawl earlier turns, summaries, or other sessions. The capture unit is the local Q&A pair only (v1 scope, #1528 Q2.b).
What to do (in order)
1. Propose slug + new-or-append + draft
In the next assistant turn after the user's promote request, output a structured proposal (do not write to disk yet):
**Proposed wiki promotion:**
- target: NEW `pages/<slug>.md` # or: APPEND `pages/<existing-slug>.md` (## Promoted YYYY-MM-DD)
- slug: `<slug>`
- title: <H1 title — display>
- draft body (markdown):
<draft markdown body — see Q5 / Q6 below for what to include>
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 · 176 lines · 112 tokens per session scan A 97618f3e3883
mc-wiki-promote is a skill published in the GitHub repository receptron/mulmoclaude (347 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 1,976 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 2026-08-30.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…