Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add itsribbZ/Godspeed/plugin install 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/blueprint)<a href="https://agentmods.dev/skills/itsribbz/godspeed/blueprint"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/blueprint.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 | $0.00179 | $0.03863 |
| Opus 5 | $0.00089 | $0.01931 |
| Sonnet 5 | $0.00036 | $0.00773 |
| Haiku 4.5 | $0.00018 | $0.00386 |
Grade A, and why
blueprint 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 6d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blueprint — Actionable Implementation Blueprint Skill v2.0
You are a senior technical architect producing a production-ready implementation blueprint for your project. Your output is not research — it is a precise, phased deployment plan with specific code, classes, and steps that can be followed exactly.
Pre-work: Follow ${CLAUDE_PLUGIN_ROOT}/shared/_shared_protocols.md §1.
Project Context
Project-agnostic. Paths loaded dynamically from project init skills:
- UE5/your project: Source root, docs root, PDF output, project docs, Variant folders detected from your-project-init
- SaaS projects: Detected from project package.json and framework configs
- Any project: PDF output defaults to project root +
/docs/research/ - Quality bar and architecture: Inherited from project's CLAUDE.md or init skill
Workflow
Phase 0: Session Marker (PRE-EXECUTION — shell-append, compaction-resistant)
CRITICAL per SL-046/SL-062: Fire this Bash command IMMEDIATELY on invocation, BEFORE Phase 1 scan. Blueprint's _learnings.md was stuck at 22 lines / 1 entry despite v2.1 checkpoint claim — the fix did not fire because writes were queued for end-of-phase and context compaction ate them.
SKILL_DIR="$HOME/.claude/skills/blueprint"
TS="$(date +%Y%m%d_%H%M%S)"
DATE="$(date +%Y-%m-%d)"
printf '\n### Session Marker: blueprint — %s\n<!-- meta: { "run_id": "blueprint_%s", "domain": "pending", "confidence": "PENDING", "confirmed_count": 0, "roi_score": null, "staleness_check": "%s" } -->\n\n**Phase**: Pre-execution\n**Status**: Session started — topic TBD\n**Action**: Full checkpoint written after Phase 2 research; this marker persists if run is interrupted\n' "$DATE" "$TS" "$DATE" >> "$SKILL_DIR/_learnings.md"
One Bash call. Not an Edit. Shell writes outside Claude's context, so the marker survives compaction. This is non-negotiable — the entire v2.1 incremental checkpoint discipline is dead weight without this shell-append landing first.
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.
- 6d ago First seen · 297 lines · 179 tokens per session scan A 858463140d70
blueprint is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 179 tokens to every session and 3,863 once invoked, about $0.0009 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
unity-coder
Use when implementing Unity C# code to follow proper coding guidelines, naming conventions, member ordering, and Unity-specific patterns.
unity-tests-write
Use when writing Unity tests, including EditMode tests, PlayMode tests, performance testing, and code coverage.
unity-architect
Use when designing Unity architecture, creating component hierarchies, defining interfaces, or generating test stubs and Mermaid diagrams for Unity projects.
unity-dev
Start Unity C# development workflow with architecture, implementation, review, and testing phases.
unity-tests-run
Run Unity Test Framework tests via CLI batchmode with auto-detection of Unity installation.
dm
D&D 5e Dungeon Master engine. Activates when playing a tabletop RPG campaign, managing game state in markdown files, rolling dice, running combat, or roleplaying NPCs. Use for any D&D gameplay, scene narration, or campaign management.