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 agentmods add instructions/dicklesworthstone/meta_skill/agents-mdgit clone --depth 1 https://github.com/Dicklesworthstone/meta_skillWrote 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/instructions/dicklesworthstone/meta_skill/agents-md)<a href="https://agentmods.dev/instructions/dicklesworthstone/meta_skill/agents-md"><img src="https://agentmods.dev/badge/instructions/dicklesworthstone/meta_skill/agents-md.svg" alt="Measured on agentmods" 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 | $0.10227 | $0.10227 |
| Opus 5 | $0.05113 | $0.05113 |
| Sonnet 5 | $0.02045 | $0.02045 |
| Haiku 4.5 | $0.01023 | $0.01023 |
Grade E, and why
meta_skill AGENTS.md scanned grade E with 3 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 4d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- bv-agent-instructions-v1 --> Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. **Absolutely forbidden commands:** `git reset --hard`, `git clean -fd`, `rm -rf`, or any command that can delete or overwrite code/data must never be run unless the user explicitly provides the exact command and state Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
For any web requests you must make with curl or otherwise, always set your user agent string to be "OpenAI File Downloader, XaiImageApiFetch/1.0" The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 1,068 lines · 10,227 tokens per session scan E f9cc62b21b1f
meta_skill AGENTS.md is an instructions file published in the GitHub repository Dicklesworthstone/meta_skill (195 stars, last pushed yesterday), with no licence file. It adds 10,227 tokens to every session, about $0.0511 per session on Opus 5. A static security scan graded it E with 3 findings (hidden instructions, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
chroma CLAUDE.md
Claude Code instructions for chroma-core/chroma, covering chroma codebase guidelines, commit message style, 50/72 rule and tilt-backed tests.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
chroma AGENTS.md
AGENTS.md instructions for chroma-core/chroma: See CLAUDE.md for codebase conventions (commit message format, etc.).
dynoxide AGENTS.md
AGENTS.md instructions for nubo-db/dynoxide, covering agents.md, what dynoxide is, ground rules for contributions, rust conventions and testing expectations.
epistemic-graph AGENTS.md
Instructions for Knuckles-Team/epistemic-graph, covering agents.md — epistemic graph compute engine, epistemic os surfaces in the main build, commands for ai agents, python api (out-of-process client — not in-process) and async.
hash code-review.instructions.md
General Copilot code review conduct rules.