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 KevinZai/commander --skill ccc-prompt-fixgit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/ccc-prompt-fix)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-prompt-fix"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-prompt-fix.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.01250 |
| Opus 5 | $0.00020 | $0.00625 |
| Sonnet 5 | $0.00008 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
ccc-prompt-fix 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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-prompt-fix — Auto Prompt Fixer
Take a rough prompt and hand back a sharper one — with the why, so you learn the pattern instead of just copying the fix. Grounded in the Claude Code prompt library (skills/claude-code-library/): 52 field-tested prompts + the 6 patterns behind all of them.
This is a coach, not a black box. Every rewrite names which pattern it applied, so the next prompt you write yourself is already better.
Modes
| You type | It does |
|---|---|
$ccc-prompt-fix <your prompt> |
Fix — diagnose + rewrite that prompt |
$ccc-prompt-fix last |
Fix the last prompt you sent this session (read from the transcript) |
$ccc-prompt-fix for <task> |
Suggest — pull the best matching prompt from the library for that task |
$ccc-prompt-fix score <prompt> |
Score — rate 0–6 on the patterns, no rewrite (quick gut-check) |
$ccc-prompt-fix (no args) |
Ask (via AskUserQuestion) which of the above you want |
The rubric — the 6 patterns (from the library)
Diagnose every prompt against these. A missing pattern is a fix opportunity; not every prompt needs all six, but each absent one is a question to ask.
- Outcome, not steps — says what, lets Claude find the how. ❌ "open X, change Y, then Z" ✅ "add rate limiting to the public API; keep existing tests green"
- A way to check its own work — includes run/test/compare/verify so it iterates instead of stopping at looks done. ✅ "write the migration, run it against dev, confirm the schema matches"
- A reference to match — names an existing file/test/pattern. ✅ "add a settings page following the profile page's layout"
- A measurable target — metric + threshold so "done" is unambiguous. ✅ "get the bundle under 200KB and show me what you cut"
- The artifact, pasted — errors/logs/screenshots or
@fileinstead of description. ✅ "why is the build failing? @build.log" - How to answer — format, length, audience. ✅ "explain the retry logic as an HTML page with a diagram, then open it"
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.
- 8d ago First seen · 84 lines · 41 tokens per session scan A b6070fe10b77
ccc-prompt-fix is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,250 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 skills, from other repositories
gpt-5-4-prompting
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin.
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
llm-evaluation
Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
prompt-engineering-patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.
prompt-library
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.