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/itsribbz/godspeed/initnpx skills add itsribbZ/Godspeed --skill initgit clone --depth 1 https://github.com/itsribbZ/GodspeedWhat 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 | $0.00083 | $0.02340 |
| Opus 5 | $0.00042 | $0.01170 |
| Sonnet 5 | $0.00017 | $0.00468 |
| Haiku 4.5 | $0.00008 | $0.00234 |
Grade B, and why
init scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
TICK=$(cat ~/.claude/telemetry/brain/godspeed_count.txt 2>/dev/null || echo 0) How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init — Session Briefing + Health
Point init at a folder, get back a project description and the context you
need to start working. Pairs with close-session so the two together form a
lossless session loop.
Trigger
"init", "/init", "start session", "initialize", "begin session", "init this project"
Phase 0: Load Foundation (grep-first — keep context light)
Never bulk-read the shared files. Pull only the entries tagged for init or ALL:
grep -B1 -A10 "applies_to.*init\|applies_to.*ALL" \
${CLAUDE_PLUGIN_ROOT}/shared/_shared_protocols.md 2>/dev/null
grep -B1 -A10 "applies_to.*init\|applies_to.*ALL" \
${CLAUDE_PLUGIN_ROOT}/shared/_shared_learnings.md 2>/dev/null
Skip silently if the shared files don't exist — init must never block on missing context.
Phase 1: Scan the Folder
Figure out what project this is. One parallel batch — don't iterate:
echo "CWD: $PWD"
ls -A | head -30
Then detect the project type from signal files (first match wins, multiple signals reported as "multi-stack"):
| Signal file(s) | Project type |
|---|---|
package.json |
Node / TypeScript |
pyproject.toml, requirements.txt, setup.py |
Python |
Cargo.toml |
Rust |
go.mod |
Go |
*.uproject, Source/*/*.Build.cs |
Unreal Engine 5 |
CMakeLists.txt |
C / C++ |
*.csproj, *.sln |
C# / .NET |
Gemfile |
Ruby |
pom.xml, build.gradle |
Java / Kotlin |
.claude-plugin/plugin.json |
Claude Code plugin |
If it's a git repo, grab the state (one call, bounded output):
git -C "$PWD" log --oneline -5 2>/dev/null
git -C "$PWD" status --short 2>/dev/null | head -20
git -C "$PWD" branch --show-current 2>/dev/null
Skip git calls cleanly if not a repo.
Phase 2: Load Prior Context
Read files that carry session-to-session context, all in one parallel batch. Read only the tail of long files — the latest entries are what matters at session start.
| File | Read pattern | Purpose |
|---|---|---|
./CLAUDE.md |
full read if < 5K, else tail 200 lines | Project rules + personal instructions — binding for the session |
./README.md |
tail 100 lines | Project overview / description |
./project_status.md |
tail 150 lines | Most recent session entry |
./MEMORY.md |
full read (index file, should stay small) | Memory index |
./.claude/settings.json |
full read if present | Hooks, permissions, env vars |
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.
- yesterday First seen · 232 lines · 83 tokens per session scan B 6d8d70d65815
init is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 2,340 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
clawrouter
Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 76 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data…
surf
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/ covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT…
polymarket-trading
Use when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools). Covers setup (deposit wallet, funding, approvals), buy/sell with confirm gating, positions, redeeming winnings, geoblock handling, and the end-to-end flow.
release
Use this skill for EVERY ClawRouter release. Enforces the full checklist — version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release. No step can be skipped.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.