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/yaleh/meta-ccWrote 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/yaleh/meta-cc/prompt-find)<a href="https://agentmods.dev/commands/yaleh/meta-cc/prompt-find"><img src="https://agentmods.dev/badge/commands/yaleh/meta-cc/prompt-find/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/yaleh/meta-cc/prompt-find"><img src="https://agentmods.dev/badge/commands/yaleh/meta-cc/prompt-find.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 | $0.00012 | $0.00892 |
| Opus 5 | $0.00006 | $0.00446 |
| Sonnet 5 | $0.00002 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
prompt-find scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionslowSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
offer: "Show full prompt? Enter ID or 'q' to quit" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Library Search
λ(keywords) → search_results | keywords := "$@"
Execution
search :: Keywords → Results search(K) = { library: get_library_path(),
if (not exists(library)): display: "No prompt library found. Save your first prompt with '/meta Refine prompt: '", return: empty,
files: glob(library + "*.md"),
if (empty(files)): display: "Library is empty. Save your first prompt with '/meta Refine prompt: '", return: empty,
matches: ∀file ∈ files: { metadata: parse_frontmatter(file), content: read_file(file), score: calculate_match_score(K, metadata, content) } where score > 0,
sorted: sort_desc(matches, m → m.score),
display: format_results(sorted, K),
if (|sorted| > 0): offer: "Show full prompt? Enter ID or 'q' to quit" }
get_library_path :: () → Path get_library_path() = project_root() + "/.meta-cc/prompts/library/"
parse_frontmatter :: FilePath → Metadata parse_frontmatter(F) = {
Extract YAML frontmatter (lines 2-12 typically)
Fields: id, title, category, keywords, usage_count, updated
}
calculate_match_score :: (Keywords, Metadata, Content) → Score calculate_match_score(K, M, C) = { keyword_matches: count_matches(K, M.keywords ∪ extract_text(M.title)), content_matches: count_matches(K, C.original_prompts), category_matches: count_matches(K, M.category),
score: (keyword_matches * 3) + (content_matches * 2) + (category_matches * 1) }
format_results :: ([Matches], Keywords) → Display format_results(M, K) = { header: "Found " + |M| + " prompts matching: " + K, separator: "─" * 80,
table: ∀match ∈ M: format_row(match),
footer: "\nUse '/prompt-show ' to view full prompt" }
format_row :: Match → String format_row(M) = sprintf( "%-40s %-15s %-8s %s", M.metadata.id, M.metadata.category, "★" * min(5, M.score / 2), # Star rating truncate(M.metadata.title, 50) )
Implementation
Execute the following steps:
- Check library exists:
if [ ! -d .meta-cc/prompts/library/ ]; then echo "No prompt library found." echo "Save your first prompt with: /meta Refine prompt: <your-prompt>" exit 0 fi
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 · 125 lines · 12 tokens per session scan A 1d328f0022e9
prompt-find is a command published in the GitHub repository yaleh/meta-cc (21 stars, last pushed 18d ago), licensed MIT. It adds 12 tokens to every session and 892 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
launch-an-ai-feature
Workflow recipe — take an AI/LLM feature from a probabilistic-aware PRD to a launch-ready model card by chaining 5 skills.
prompt-history
Manage history of created and optimized prompts.
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
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.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.