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/fastrevmd-lab/fwskillsshare/agents-mdgit clone --depth 1 https://github.com/fastrevmd-lab/fwskillsshareWrote 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/fastrevmd-lab/fwskillsshare/agents-md)<a href="https://agentmods.dev/instructions/fastrevmd-lab/fwskillsshare/agents-md"><img src="https://agentmods.dev/badge/instructions/fastrevmd-lab/fwskillsshare/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 | $0.00948 | $0.00948 |
| Opus 5 | $0.00474 | $0.00474 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
fwskillsshare AGENTS.md 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 3d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firewall skills repository instructions
Purpose and architecture
This repository packages firewall parsing, conversion, diff, audit, compliance,
and Juniper SRX operational skills. Each skills/<name>/ subtree contains a
SKILL.md, references, metadata, and optional fixtures/scripts. The parsing
skills share a normalized schema whose copies must remain byte-identical.
Setup and development
- Install the golden workstation baseline and run
just setup. - Skills are Markdown-first; use repository validation scripts instead of inventing a build system. Installation tests must target disposable paths.
- Vendor syntax and compliance claims require authoritative evidence or an explicit unsupported/uncertain classification.
Required checks
- Run
just fmt,just lint,just test, andjust guardoffline. just integrationintentionally does not contact devices; real-device validation requires a separate explicit task and approval.- Run
just securityandjust release-checkbefore handoff.
Skill description constraints
Two different limits, often confused:
- Per skill: 1,024 characters, hard. Codex enforces this. Verified against
codex-cli 0.147.0, whose binary carries
Description is too long ({n} characters). Maximum is 1024 characters.scripts/check-skill-packages.pyerrors on it. - Combined across all skills: soft, warn only. There is no cliff. Codex
0.147.0 truncates skill metadata to fit its context budget and reports what it
did —
ext/skills/src/render_observability.rsemitsbudget_limit,included_skills,omitted_skills,truncated_description_chars_per_skillandtruncated_skill_descriptions. Discovery also runs through a dynamic selector (ext/skills/src/dynamic_skill_selector/), so the flat concatenated list is a fallback, not the primary path. The checker warns aboveCOMBINED_DESCRIPTION_WARNand never fails on it.
A hard combined cap was previously enforced at 8,000 characters with no recorded provenance. It scaled the ceiling with skill count — at 26 skills the repo sat at 7,998 of 8,000 — and would have blocked the next skill for a limit the runtime degrades gracefully around. If you change these numbers, cite the Codex version you measured against, as above.
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.
- 3d ago First seen · 89 lines · 948 tokens per session scan A e56e0ffcc57a
fwskillsshare AGENTS.md is an instructions file published in the GitHub repository fastrevmd-lab/fwskillsshare (8 stars, last pushed 6d ago), licensed MIT. It adds 948 tokens to every session, about $0.0047 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 instructions, from other repositories
netcanon AGENTS.md
Instructions for netcanon/netcanon, covering netcanon — contributor directives, two concerns, one fastapi app, parallel platform development, platform-specific exceptions and feature parity checklist.
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
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
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).