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 commands/itsribbz/godspeed/godspeed-settingsgit clone --depth 1 https://github.com/itsribbZ/GodspeedWrote 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/commands/itsribbz/godspeed/godspeed-settings)<a href="https://agentmods.dev/commands/itsribbz/godspeed/godspeed-settings"><img src="https://agentmods.dev/badge/commands/itsribbz/godspeed/godspeed-settings.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 | $0.00042 | $0.00346 |
| Opus 5 | $0.00021 | $0.00173 |
| Sonnet 5 | $0.00008 | $0.00069 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
godspeed-settings 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 5d 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.
What it actually says
Display the current Brain routing manifest settings so the user can see what's tunable.
Instructions for the model:
- Read
${CLAUDE_PLUGIN_ROOT}/automations/brain/routing_manifest.tomlwith theReadtool. - Render a compact summary organized by section:
- Signal weights (
[weights]) — 10 signals with their percentage contributions to the final score - Tier thresholds (
[thresholds]) — score boundaries for S0/S1/S2/S3/S4 - Tier → model mapping (
[tier_map.Sn]) — model + effort + extended-thinking budget per tier - Keyword lists (
[keywords]) — reasoning/multi-step/code-action/ambiguity/tool-calls triggers (counts per list) - Guardrails (
[guardrails.*]) — active hard-minimum-score overrides (list names + descriptions) - Skill tier overrides (
[skills]) — explicit S-tier assignments for shipped skills
- Signal weights (
- At the bottom, print:
To tune: edit ${CLAUDE_PLUGIN_ROOT}/automations/brain/routing_manifest.toml, then run: python ${CLAUDE_PLUGIN_ROOT}/automations/brain/manifest_to_json.py - Keep the output scannable — tables or compact lists, no walls of prose.
This command is read-only — do NOT modify the manifest. Display values exactly as stored.
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.
- 5d ago First seen · 20 lines · 42 tokens per session scan A be687a28697d
godspeed-settings is a command published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 346 once invoked, about $0.0002 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 commands, from other repositories
stats
Show model-routing stats - dispatches and real token volume kept off the session model. Args - --days N (window size, default 7), --ago M (shift window M days back), --session (only sessions on that model, e.g. fable).
doctor
Diagnose what is busting Claude Code's DeepSeek prefix cache.
benchmark
Run the Permafrost cache benchmark (offline emulator, no API key).
status
Show Permafrost's live DeepSeek cache hit rate and dollar savings.
wrap
Explain how to launch Claude Code through the Permafrost proxy.
init
Install the formatters this repository needs, with every command visible before it runs.