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 bengous/claude-code-plugins --skill meta-promptgit clone --depth 1 https://github.com/bengous/claude-code-pluginsWrote 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/bengous/claude-code-plugins/meta-prompt)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/meta-prompt"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/meta-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/skills/bengous/claude-code-plugins/meta-prompt"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/meta-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 | $0.00069 | $0.00772 |
| Opus 5.5 | $0.00028 | $0.00309 |
| Sonnet 5.5 | $0.00014 | $0.00154 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
meta-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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Prompt
Write the prompt another agent will receive. The prompt carries the user's intention, at the user's level of certainty. It is not a plan.
Input
$ARGUMENTS
No arguments: the request is the task discussed in this conversation.
Preserve intention and certainty
The executor treats everything in the prompt as the user's own words. So nothing enters the prompt that the user did not decide.
- A directive the user stated ("use this lib", "do it like X", "not in that file") is kept as a directive, in the user's terms.
- Everything the user left open stays open. Never pick an approach, a library, a file layout, a sequence of steps, or a scope the user did not pick. Never add requirements, acceptance criteria, or examples the user did not give.
- When the request reads as exploration (confused ideas, "I'm not sure", "let's think about"), say so in the prompt: the executor is to think it through with the user before implementing.
- Questions go into the prompt, under Open, for the executor to ask. Do not ask them here.
Mine the conversation
When the request follows a discussion, the conversation holds facts the executor needs: decisions made and why, constraints and anti-patterns the user expressed, prior art they pointed at. Carry those in, filtered to what bears on the task. The executor reads cold: no shorthand from this conversation ("as discussed", "the earlier approach"). Every reference resolves for a reader with zero context.
Verify references
Check that each file, symbol, or convention the request names exists. Pick up the
conventions in CLAUDE.md, AGENTS.md, and .claude/rules/ that bear on the task, unless
the harness already put them in context.
Report what you found as facts: "exists at path", "does not exist", "already done in path", "unverified". When the repo contradicts the request, state the contradiction under Context and keep the request as the user made it. Retargeting is the executor's conversation with the user, not yours.
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.
- 1mo ago First seen · 75 lines · 69 tokens per session scan A e12b68a1499c
meta-prompt is a skill published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 772 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
tencent-docs
A Tencent Docs assistant for creating, reading, editing, organizing, importing, and exporting online documents, spreadsheets, presentations, diagrams, and forms.
wechat-search
Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.