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.
git 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-info)<a href="https://agentmods.dev/commands/itsribbz/godspeed/godspeed-info"><img src="https://agentmods.dev/badge/commands/itsribbz/godspeed/godspeed-info.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 5.1 | $0.00030 | $0.01415 |
| Opus 5 | $0.00015 | $0.00707 |
| Sonnet 5 | $0.00006 | $0.00283 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
godspeed-info 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 7d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/godspeed-info — Pipeline Overview
Render the godspeed pipeline summary. Read-only — does not trigger execution mode.
Execution
- Read
~/.claude/telemetry/brain/godspeed_count.txtwith theReadtool to get the current tick count. Fallback to0if missing or unreadable. - Compute
next_scan_at= smallest multiple of 33 strictly greater than current tick. (current=0 → 33; current=5 → 33; current=33 → 66; current=40 → 66.) - Compute
runs_away=next_scan_at - current_tick. - Print the template below verbatim inside a single fenced code block, substituting
{TICK}/{NEXT_SCAN}/{RUNS_AWAY}with the live values. - After rendering, write one short closing line (e.g.
Info mode rendered. Say "godspeed" for execution mode.) and STOP. No further tool calls. No triage. No Phase -1 tick. Info mode is render-and-stop.
Template (substitute live values for {TICK} / {NEXT_SCAN} / {RUNS_AWAY})
═══════════════════════════════════════════════════════════════
GODSPEED v4.10 — MAX EXECUTION MODE
═══════════════════════════════════════════════════════════════
PIPELINE FLOW
─────────────
[-1] TICK Self-audit counter (every 33 ticks → brain scan)
current: {TICK} next: {NEXT_SCAN} ({RUNS_AWAY} away)
│
▼
[0.5] BRAIN Severity classify S0–S5 → tier→model bind
│ (S0/S1=Haiku · S2/S3=Sonnet · S4/S5=Opus)
│ S3+ → auto-dispatch Zeus
│
▼
[1-3] TRIAGE → ROUTE → DEPLOY
│ Domain-adaptive priority P0→P3, Pipeline Router,
│ parallel tool execution where possible
│
▼
[3i] COST GUARD Mid-flight budget enforcement (1.5× soft-cap)
│ Verdict: OK / BUDGET_EXCEEDED
│ Receipts → ~/.claude/telemetry/brain/cost_efficiency.jsonl
│
▼
[4] ESCALATE L1 narrow → L2 instrument → L3 research →
│ L3.5 advisor (Sonnet stuck → Opus rescue) →
│ L4 ask user → L5 flag blocker
│
▼
[5] RECONCILE Zero-missed-tasks verification
│
▼
[6] LEARN zeus gate-write → Oracle score → Mnemos Recall
SHIPPED SKILLS (18 total — domain-agnostic methodology)
───────────────────────────────────────────────────────
HOMER PANTHEON (orchestrator-worker stack)
zeus L2 Orchestrator — decomposes S3+ tasks
calliope L3 Epic Research Muse (web + synthesis)
clio L3 Code Archaeology Muse (file:line maps)
urania L3 Measurement Muse (telemetry receipts)
sybil L4 Advisor escalation (advisor_20260301)
mnemos L5 3-tier memory (Core / Recall / Archival)
oracle L7 Critic — scores synthesis, gates writes
brain L1 Severity classifier (S0-S5 router)
PIPELINE SKILLS (methodology)
holy-trinity Diagnose → Research → Implement → Verify
devTeam Code architecture scoring (7 Laws)
profTeam Multi-agent parallel research engine
professor Single-topic deep research + PDF
blueprint Implementation plan from codebase
cycle 3-pass blueprint refinement
UTILITY SKILLS
close-session Session closure + learning persistence
verify Build / test verification (multi-stack)
init Project initialization router
godspeed This skill — max-execution mode
COST GUARD BUDGETS (Phase 3i, per agent invocation)
───────────────────────────────────────────────────
S0 $0.005 S1 $0.02 S2 $0.10
S3 $0.50 S4 $2.00 S5 $5.00
1.5× soft-cap → BUDGET_EXCEEDED verdict mid-flight
BRAIN ROUTING (always active, zero config)
──────────────────────────────────────────
Severity tiers S0-S2 → direct tool | S3-S5 → Zeus orchestrator
Subagents Sonnet via CLAUDE_CODE_SUBAGENT_MODEL env var
Skills Pinned per skill frontmatter (S-tier)
Advisor API L3.5 — Sonnet stuck → Opus rescue (max 2/session)
Self-audit every 33 ticks → inline `brain scan`
SLASH COMMANDS
──────────────
/godspeed-info This pipeline summary (you are here)
/godspeed-settings Render current routing manifest (weights, tiers, guardrails)
/brain-score <text> Classify any prompt on the S0-S5 scale
TRIGGERS
────────
"godspeed" / GODSPEED Full max execution mode
"stuck" mid-task L3.5 advisor escalation
Every 33 ticks Inline `brain scan` self-audit
SACRED RULES ACTIVE (11)
────────────────────────
#1 Truthful #2 No delete #3 No revert
#4 Only-asked #5 Diag = feature #6 No creative
#7 Edit only #8 No auto-close #9 No menus
#10 godspeed = command #11 AAA quality
═══════════════════════════════════════════════════════════════
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.
- 7d ago First seen · 126 lines · 30 tokens per session scan A 4332a0c91c9b
godspeed-info is a command published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,415 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
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
ccc-orchestrate
Sequential and tmux/worktree orchestration guidance for multi-agent workflows.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
design
A command that turns an existing plan into a detailed technical design for building the feature.
complete
Signal that a skill's work is complete. Triggers downstream subscriptions with "when": "complete" timing. Automatically invoked — do not run manually.