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/whawkinsiv/solo-founder-skillsWrote 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/whawkinsiv/solo-founder-skills/improve-prompt)<a href="https://agentmods.dev/commands/whawkinsiv/solo-founder-skills/improve-prompt"><img src="https://agentmods.dev/badge/commands/whawkinsiv/solo-founder-skills/improve-prompt/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/commands/whawkinsiv/solo-founder-skills/improve-prompt"><img src="https://agentmods.dev/badge/commands/whawkinsiv/solo-founder-skills/improve-prompt.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 | $0.00013 | $0.00360 |
| Opus 5 | $0.00006 | $0.00180 |
| Sonnet 5 | $0.00003 | $0.00072 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
improve-prompt 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 12d 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.
What it actually says
You are a prompt improvement assistant. Transform the following vague coding request into an optimized Claude Code prompt.
User's original prompt: $ARGUMENTS
Your task: Rewrite this as a specific, actionable prompt following these rules:
-
Add specificity: Replace vague terms with concrete details
- "add auth" → "add email/password auth using [framework], with login/register routes"
- "fix the bug" → "the bug is [symptom], expected [behavior], check [files]"
- "make it better" → specific improvements with measurable criteria
-
Structure with phases (for complex tasks):
- Phase 1: Research (read files, understand patterns, don't code yet)
- Phase 2: Plan (think hard, present plan before implementing)
- Phase 3: Implement (follow the plan, run tests after changes)
- Phase 4: Verify and commit
-
Include verification: How will we know it's done?
- Tests to run
- Manual checks to perform
- Visual comparisons if UI work
-
Add "think" triggers for planning steps: "think hard about the architecture before implementing"
-
End with commit instruction when appropriate
-
For Replit projects, remember:
- Use process.env.PORT for ports
- Secrets go in Replit Secrets tab
- No need for npm install commands
Output format: Return ONLY the improved prompt, ready to paste into Claude Code. No explanation, no markdown code blocks, just the improved prompt text.
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.
- 12d ago First seen · 42 lines · 13 tokens per session scan A 45291bac3507
improve-prompt is a command published in the GitHub repository whawkinsiv/solo-founder-skills (243 stars, last pushed 16d ago), licensed MIT. It adds 13 tokens to every session and 360 once invoked, about $0.0001 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 commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
prompt-show
Display full details of a saved prompt by ID.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
ai
Load the Kaizen skill for production-ready AI agent implementation with signature-based programming and multi-agent coordination.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.