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 solanabr/solana-ai-kit --skill idea-sprintgit clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/solanabr/solana-ai-kit/idea-sprint)<a href="https://agentmods.dev/skills/solanabr/solana-ai-kit/idea-sprint"><img src="https://agentmods.dev/badge/skills/solanabr/solana-ai-kit/idea-sprint/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/solanabr/solana-ai-kit/idea-sprint"><img src="https://agentmods.dev/badge/skills/solanabr/solana-ai-kit/idea-sprint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 7 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 82 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00058 | $0.01428 |
| Opus 5 | $0.00029 | $0.00714 |
| Sonnet 5 | $0.00012 | $0.00286 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
idea-sprint 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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Sprint
Interview → necessity gate → 3 candidates → score → go/no-go. Output is a decision, not a brainstorm.
Context handoff
- At start: read
.claude/context/idea.mdand.claude/context/build.mdif present — resume from prior state instead of re-interviewing. - On completion: write/update
.claude/context/idea.mdwith the chosen idea, scores, validation evidence, and open risks. Downstream skills (pitch-deck, hackathon) read it.
Workflow
1. Blunt interview
No flattery. Short, pointed questions, one at a time, until three things are explicit:
- Edge — what the founder knows/can do that most can't (domain, distribution, tech)
- Constraint — time, money, team, chain commitments
- Wedge — the niche entry point, not the end-state vision
Push back on vague answers. "DeFi for everyone" is not a wedge. Full question bank: interview-framework.md.
2. Crypto-necessity gate
Kill question: "What gets worse if I remove the blockchain?" If the answer is vague, aesthetic, or marketing-driven — redirect the idea before scoring it. Pass criteria and redirect patterns: crypto-necessity-test.md.
3. Exactly 3 candidates
Generate three diverse candidates (different mechanisms/markets, not three flavors of one idea). For each:
- One-line pitch + target user
- Winner case — what's true in 18 months if it works
- Bear case — the most likely way it dies
Seed from datasets + live landscape (below), then combine with fresh research. Datasets are inspiration, not constraints.
4. Score /15
Each candidate, 0–3 per dimension (full anchors: scoring-rubric.md):
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.
- 10d ago First seen · 87 lines · 58 tokens per session scan A 588367581eaa
idea-sprint is a skill published in the GitHub repository solanabr/solana-ai-kit (101 stars, last pushed 20d ago), licensed MIT. It adds 58 tokens to every session and 1,428 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
jahro-logging
Reviews and improves Debug.Log usage in Unity C# projects following structured logging principles: context tags, severity contracts, boundary-based placement, and criticality tiers. Detects common antipatterns (naked Debug.Log, logging in Update, stringly-typed errors), adds missing logs at system/state/error/external…
jahro-migration
Analyzes existing debug systems (IMGUI menus, custom loggers, cheat frameworks, performance HUDs) and generates incremental migration plans to Jahro equivalents. Use when the user wants to replace a custom debug UI, migrate from an existing console or cheat system, switch to Jahro, or has OnGUI debug code they want to…
jahro-troubleshooting
Diagnoses common Jahro issues using decision trees: commands not appearing, watcher not updating, console not opening, snapshots failing, launch button missing. Use when the user reports something not working, missing, broken, or unexpected with Jahro, or when generated Jahro code doesn't behave as expected.
jahro-commands
Analyzes C# classes and generates [JahroCommand] attributes with correct syntax, RegisterObject patterns, and group organization. Use when the user wants to add runtime commands, cheats, or debug actions to Unity classes, or mentions JahroCommand, console commands, runtime cheats, or debug actions.
jahro-watcher
Analyzes C# fields and properties and generates [JahroWatch] attributes with groups and performance-safe patterns. Use when the user wants to monitor variables at runtime, add watchers, track game state, replace Debug.Log polling, or mentions JahroWatch, real-time inspection, or variable monitoring.
jahro-production
Configures Jahro lifecycle controls for safe production deployment including JAHRODISABLE, auto-disable, and build validation. Use when the user mentions production builds, release builds, disabling Jahro, shipping, CI/CD, lifecycle controls, or production safety.