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 AiAi-Mastermind/aiai-mastermind-tools-and-skills --skill fabsolgit clone --depth 1 https://github.com/AiAi-Mastermind/aiai-mastermind-tools-and-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/aiai-mastermind/aiai-mastermind-tools-and-skills/fabsol)<a href="https://agentmods.dev/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/fabsol"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/fabsol/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/aiai-mastermind/aiai-mastermind-tools-and-skills/fabsol"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/fabsol.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 | $0.00069 | $0.01470 |
| Opus 5 | $0.00034 | $0.00735 |
| Sonnet 5 | $0.00014 | $0.00294 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
fabsol scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "${MODEL_ROUTER_URL:-http://127.0.0.1:8317}/v1/models" \ How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FabSol - the orchestrator + worker build flow
This is the flow that combines the two models. The name is Fable + Sol, but it
works with any pair: your main session model orchestrates, and whatever model
MODEL_ROUTER_MODEL points at does the building.
You are the ORCHESTRATOR, running on this session's normal login - NEVER route
this session through the proxy. All building is delegated to the WORKER model
via headless claude -p calls through the local proxy (CLIProxyAPI), which
holds the user's other subscription logins.
Configuration (all changeable - see the README's "Change the defaults")
| Setting | Env var | Ships as |
|---|---|---|
| Proxy URL | MODEL_ROUTER_URL |
http://127.0.0.1:8317 |
| Proxy key | MODEL_ROUTER_KEY |
my-proxy-key (an api-keys entry in your proxy config.yaml) |
| Worker model | MODEL_ROUTER_MODEL |
gpt-5.6-sol |
| Worker effort | MODEL_ROUTER_EFFORT |
low |
| Worker turn cap | --max-turns in the call below |
20 |
The worker ships cheap-and-fast (low effort, bare harness, 20-turn cap) and
holds up because the spec you write carries the thinking. If builds keep
missing acceptance criteria, raise the effort to medium. Bigger multi-file
tasks getting cut off: raise the turn cap.
The worker delegation call (Bash, one per build task)
ANTHROPIC_BASE_URL="${MODEL_ROUTER_URL:-http://127.0.0.1:8317}" \
ANTHROPIC_AUTH_TOKEN="${MODEL_ROUTER_KEY:-my-proxy-key}" \
claude -p "<self-contained task spec>" \
--model "${MODEL_ROUTER_MODEL:-gpt-5.6-sol}" \
--effort "${MODEL_ROUTER_EFFORT:-low}" \
--bare --max-turns 20 --permission-mode acceptEdits \
&& ls -la <expected output paths> \
&& grep -c "<acceptance marker>" <built file>
--bare is safe for the worker because its auth comes from the env vars on the
call, not a stored login. The && ls && grep tail is not decoration - it is
how the build's proof comes back in the same tool result (rule 2 below).
ORCHESTRATOR EFFICIENCY RULES (non-negotiable)
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 · 118 lines · 69 tokens per session scan A f2a4f6e78465
fabsol is a skill published in the GitHub repository AiAi-Mastermind/aiai-mastermind-tools-and-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,470 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
wiki
Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…