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 itsribbZ/Godspeed --skill toke-initgit 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/skills/itsribbz/godspeed/toke-init)<a href="https://agentmods.dev/skills/itsribbz/godspeed/toke-init"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/toke-init/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/itsribbz/godspeed/toke-init"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/toke-init.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 | $0.00047 | $0.01151 |
| Opus 5.5 | $0.00019 | $0.00460 |
| Sonnet 5.5 | $0.00009 | $0.00230 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade B, and why
toke-init scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
TICK=$(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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toke Init — Session Pre-Flight
Invoke at session start to load Toke context and verify system health.
Project Paths
| Item | Path |
|---|---|
| Toke root | $TOKE_ROOT (set via env var; defaults to the cloned repo location) |
| Project status | ~/.claude/projects/<current-slug>/memory/project_status.md |
| Memory index | ~/.claude/projects/<current-slug>/memory/MEMORY.md |
| Global settings | ~/.claude/settings.json |
| Installed skills | ~/.claude/skills/ |
| Slash commands | ~/.claude/commands/ |
Phase 1: Load (parallel)
Read these in one parallel batch so nothing blocks:
- Project status —
~/.claude/projects/<current-slug>/memory/project_status.md(if exists) — where we left off - Memory index —
~/.claude/projects/<current-slug>/memory/MEMORY.md(if exists) — pointer list - Toke README —
$TOKE_ROOT/README.md— big-picture refresher (optional — skip if already loaded)
If a file is missing → warn but continue. Never block init on a missing file.
Phase 2: Health Check (fast, ≤ 5 seconds)
Parallel shell block — catches broken pipelines early:
# Brain telemetry
DECISIONS=$(wc -l < ~/.claude/telemetry/brain/decisions.jsonl 2>/dev/null || echo 0)
TOOLS=$(wc -l < ~/.claude/telemetry/brain/tools.jsonl 2>/dev/null || echo 0)
TICK=$(cat ~/.claude/telemetry/brain/godspeed_count.txt 2>/dev/null || echo 0)
echo "Brain: ${DECISIONS} decisions, ${TOOLS} tool calls, tick ${TICK}"
# Homer pantheon
python $TOKE_ROOT/automations/homer/homer_cli.py status 2>&1 | head -12
# Mnemos store
python $TOKE_ROOT/automations/homer/mnemos/mnemos.py health 2>&1 | head -12
# Zeus CLI
python $TOKE_ROOT/automations/homer/zeus/zeus_cli.py status 2>&1 | tail -5
Report inline. Flag any layer that fails its health check. Do NOT block init on a health warning — surface it in the briefing.
Phase 3: Briefing
Render a one-screen summary — real data from Phase 1+2, no placeholders:
═══════════════════════════════════════
TOKE — SESSION READY
═══════════════════════════════════════
LAST SESSION: [date from project_status.md] — [one-line summary]
Completed: [bullets from status]
In-Progress:[bullets from status]
Next Up: [bullets from status]
TOKE SYSTEMS:
Brain: [N] decisions logged, tick [N]
Homer: [N]/8 layers live, [N]/[N] integration tests green
Mnemos: [N] recall rows, semantic_available=[T/F]
Zeus: atomic gate-write CLI [OK/missing]
READY. What are we building?
═══════════════════════════════════════
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.
- 2mo ago First seen · 115 lines · 47 tokens per session scan B ef1aaefd34bf
toke-init is a skill published in the GitHub repository itsribbZ/Godspeed (0 stars, last pushed 24d ago), licensed MIT. It adds 47 tokens to every session and 1,151 once invoked, about $0.0002 per session on Opus 5.5. 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.
toke-init compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| toke-inititsribbZ/Godspeed | Skill | 0 | 24d ago | MIT | B | 47 | Claude Code, Codex |
| fresh-startegorfedorov/claude-context-optimizer | Skill | 130 | 10d ago | MIT | A | 60 | Claude Code |
| token-checkegorfedorov/claude-context-optimizer | Skill | 130 | 10d ago | MIT | A | 66 | Claude Code |
| ccc-resume-sessionKevinZai/commander | Skill | 6 | yesterday | MIT | A | 33 | Claude Code |
| maudejohn-broadway/maude-for-claude | Skill | 3 | yesterday | Apache-2.0 | A | 191 | Claude Code |
| g-resumeonlygian/G-Forge | Skill | 4 | 9d ago | GPL-3.0 | A | 128 | Claude Code |
| scout-consolidationRaven-Scout/scout-plugin | Skill | 17 | 1mo ago | MIT | A | 36 | Claude Code |