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/ourobx/agent-ebpf/file-style-conventionsgit clone --depth 1 https://github.com/ourobx/agent-ebpfWrote 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/ourobx/agent-ebpf/file-style-conventions)<a href="https://agentmods.dev/instructions/ourobx/agent-ebpf/file-style-conventions"><img src="https://agentmods.dev/badge/instructions/ourobx/agent-ebpf/file-style-conventions.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 | $0.00792 | $0.00792 |
| Opus 5 | $0.00396 | $0.00396 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade C, and why
file-style-conventions scanned grade C 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 today.
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.
<!-- Copilot Instruction Telemetry: This file was auto-generated by Claude Skills Manager --> How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
file-style-conventions
File Style Conventions
Two small, easy-to-violate-by-accident conventions enforced on every file write/edit:
1. No emoji outside Markdown
- Files with extension
.md(or.mdx) may contain emoji if the user asked for them — don't add emoji proactively even there. - Every other file type (source code, YAML/JSON/TOML config, shell/PS1 scripts, Dockerfiles, CI configs, etc.) must contain no emoji characters at all — including in comments, log messages, string literals, and commit messages/PR titles (these aren't files, but the same rule applies).
- Why: emoji can break strict-encoding parsers, inflate diffs with multi-byte sequences, misrender in some terminals/log viewers, and are inconsistent with this project's style.
- Before finalizing a non-
.mdfile you wrote/edited, scan for emoji (common ranges:U+1F300–U+1FAFF,U+2600–U+27BF,U+2190–U+21FFarrows used decoratively, variation selectorsU+FE0F). If found, replace with plain text (e.g.[OK]/[FAIL]instead of check/cross emoji,->instead of arrow emoji) or remove entirely.
2. YAML files end with a trailing newline
- Every
.yml/.yamlfile must end with exactly one\n(the file's last byte is a newline, and there is no trailing blank line beyond it). - This matches the POSIX "text file ends with a newline" convention, avoids
git diffshowing\ No newline at end of file, and satisfiesyamllint'snew-line-at-end-of-filerule (the default in most CI lint jobs — seeci-pipeline-debug/gitlab-pipeline-ops). - After writing/editing a
.yml/.yamlfile, verify:
or in PowerShell:tail -c1 path/to/file.yml | od -c | head -1 # should show \n, not empty$bytes = [System.IO.File]::ReadAllBytes("path/to/file.yml") $bytes[-1] -eq 10 # 10 = LF; should be True - If missing, append a single newline — don't add multiple blank lines at end of file.
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.
- today Changed c20058713bd9
- 4d ago First seen · 63 lines · 792 tokens per session scan C dd39973c27ac
file-style-conventions is an instructions file published in the GitHub repository ourobx/agent-ebpf (1 stars, last pushed today), licensed MIT. It adds 792 tokens to every session, about $0.0040 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
casbin-gateway CLAUDE.md
Claude Code instructions for apache/casbin-gateway, covering claude.md and code style.
aigis CLAUDE.md
Claude Code instructions for killertcell428/aigis, covering aigis — project guidelines, zenn記事管理(zenn cli + github連携), ディレクトリ構成, 記事の作成 and プレビュー.
preloop AGENTS.md
AGENTS.md instructions for preloop/preloop, covering preloop development guide, commands, git workflow, keep sample data generic and code style.
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
xops-cli AGENTS.md
AGENTS.md instructions for wentf9/xops-cli, covering ai 助手开发协作指南 (agents.md), 🎨 1. 编码规范 (coding standards), 📦 2. git 规范 (git standards) and 🛠️ 3. 测试、构建与 ci (testing, building & ci).
fwskillsshare AGENTS.md
Instructions for fastrevmd-lab/fwskillsshare, covering firewall skills repository instructions, purpose and architecture, setup and development, required checks and skill description constraints.