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 agentmods add skills/febradc-github/turnstile/turnstile-loop-startnpx skills add febradc-github/turnstile --skill turnstile-loop-startgit clone --depth 1 https://github.com/febradc-github/turnstileWhat 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 | $0.00050 | $0.01127 |
| Opus 5 | $0.00025 | $0.00563 |
| Sonnet 5 | $0.00010 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
turnstile-loop-start 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 2d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop Start
Process
1. Parse arguments
From $ARGUMENTS, extract:
goal(required) -- what the loop is trying to accomplish.success(required) -- the observable condition that marks the loop done.max-iterations(optional, default 3) -- hard cap; must be a positive integer.
If goal or success is missing, tell the user the required arguments and stop.
Validate max-iterations: if present and not a positive integer, tell the user and stop.
2. Determine mode
Ask the user:
Run in loop mode? [y] autonomous -- iterations run uninterrupted until done [n] manual -- you confirm each DECIDE before the loop advances
Wait for the user's reply. Accept y/yes/Y as autonomous and n/no/N as manual. Any other input: re-ask once, then stop with an explanation.
3. Generate a loop id
Construct an id of the form L-<timestamp> where <timestamp> is the current Unix timestamp in seconds (e.g. L-1721000000). This id must be unique per run.
4. Initialise state
Determine the project root: use CLAUDE_PROJECT_DIR if set, otherwise process.cwd().
Run:
const { initState } = require('<pluginRoot>/scripts/loop-state.js');
initState(id, goal, success, maxIterations, mode, projectRoot);
Tell the user:
Loop
<id>initialised. Goal: . Success: . Max iterations: . Mode: . State file: turnstile/loops//state.json
5. Query prior brain notes
Use the search_notes MCP tool to find any brain notes from previous runs that match the current goal string:
search_notes(query: goal)
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.
- 2d ago First seen · 96 lines · 50 tokens per session scan A 971f93d89d8a
turnstile-loop-start is a skill published in the GitHub repository febradc-github/turnstile (1 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,127 once invoked, about $0.0003 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
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
comfyui-node-registry
Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…
performance-analysis
Measurement approaches, profiling patterns, bottleneck identification, and optimization guidance. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.