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/okfriansyah-moh/ares/agents-mdgit clone --depth 1 https://github.com/okfriansyah-moh/aresWrote 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/okfriansyah-moh/ares/agents-md)<a href="https://agentmods.dev/instructions/okfriansyah-moh/ares/agents-md"><img src="https://agentmods.dev/badge/instructions/okfriansyah-moh/ares/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 5.1 | $0.01516 | $0.01516 |
| Opus 5 | $0.00758 | $0.00758 |
| Sonnet 5 | $0.00303 | $0.00303 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade C, and why
ares AGENTS.md 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 5d 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.
<!-- ars:source .ai/instructions/architecture.md --> How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ares
Repository Instructions
Repository Knowledge Architecture
Purpose
Define the structure and ownership model of .ai/.
See mission.md for the problem statement, product scope, and portability rationale.
Principles
- Markdown is the source of truth.
manifest.yamlis the only required configuration file. - Prefer convention over configuration. Choose obvious file names and locations over extra metadata.
- Keep file count low and information density high.
- A single opened file should explain its topic without requiring a chain of lookups.
Structure
manifest.yamlstores minimal repository identity and defaults.instructions/holds repository-wide guidance.agents/<name>/AGENT.mddefines a thin role and points to the skills it uses.skills/<name>/SKILL.mdis the authoritative source for reusable knowledge.prompts/contains reusable prompts that invoke skills without duplicating them.
Ownership
instructions/own repository-level rules and ARES-specific guidance.agents/own role boundaries and skill references.skills/own reusable methods, checklists, and output expectations.prompts/own reusable request templates.
Change Rules
- Put durable knowledge in the narrowest file that owns it.
- Prefer updating an existing file over creating a new one.
- Add
references/under a skill only when it removes real duplication. - Keep agents thin, skills universal, and prompts reusable.
Contribution Guidelines
How To Change .ai/
- Find the file that already owns the knowledge.
- Update that file directly.
- Prefer refining existing guidance over adding new files.
- Keep the result concise enough to scan quickly.
Ownership Rules
instructions/mission.mdowns ARES-specific purpose, scope, and portability rationale.instructions/architecture.mdowns.ai/structure and file ownership.instructions/owns repository-wide rules.skills/own reusable methods, checklists, and output expectations.agents/define roles, boundaries, and skill references.prompts/provide reusable request templates and should stay lean.
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.
- 5d ago First seen · 192 lines · 1,516 tokens per session scan C 1963b69d7209
ares AGENTS.md is an instructions file published in the GitHub repository okfriansyah-moh/ares (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,516 tokens to every session, about $0.0076 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
agents AGENTS.md
AGENTS.md instructions for scarletkc/agents, covering agent guidelines, environment, engineering principles, code style and testing.
codex-manager AGENTS.md
AGENTS.md instructions for ewsun22/codex-manager, covering codex manager 项目指令, 产品边界, 隐私与安全, 工程规则 and 开源文档与发布流程.
awesome-grok-build AGENTS.md
Instructions for DominikTobureto/awesome-grok-build, covering agents.md, mission, operating principles, source policy and file conventions.
mancode AGENTS.md
AGENTS.md instructions for whitelonng/mancode, covering agents.md, 命令, 模块路由, 变更约束 and mancode bootstrap.
conforme AGENTS.md
AGENTS.md instructions for maxgfr/conforme, covering project instructions, claude.md, project overview, build & test and architecture.
conforme GEMINI.md
Gemini CLI instructions for maxgfr/conforme, covering claude.md, project overview, build & test, architecture and keeping docs in sync.