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/scarletkc/agents/agents-mdgit clone --depth 1 https://github.com/scarletkc/agentsWhat 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 | $0.00703 | $0.00703 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
agents 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
Project-agnostic rules for AI agents contributing to a repository. To adopt:
copy this file into a project as AGENTS.md and prepend the project-specific
sections (structure, build/test commands, domain notes). Everything below
applies as-is to any codebase.
Environment
Use the project's own toolchain and environment: the checked-in virtualenv, lockfile, or package manager, never the system interpreter or global installs. If the project defines a canonical test or lint command, run that one; don't invent a variant. Read the project's own guidelines and existing code before the first change: established conventions beat personal defaults.
Engineering Principles
Let errors surface instead of swallowing them: degraded paths are acceptable only as deliberate, user-visible product behavior, never as silent fallbacks that make code appear to work. Fix root causes rather than papering over symptoms; if the root cause can't be pinned down, say so and state what information is missing (better diagnostics beat a speculative fix). All code is production-quality by default: no temporary, placeholder, or demo-only implementations unless explicitly requested. When requirements are unclear, ambiguous, or inconsistent, ask instead of inventing details. A change that claims to improve behavior ships with evidence: measure before flipping a default, and if your own benchmark doesn't support the claim, ship the change opt-in and say so.
Code Style
Match the surrounding code: its naming, idiom, comment density, and error
handling. Before writing new logic, look for an existing helper to reuse or
extend; if the same behavior already lives in more than one place, extract
the smallest shared helper that makes sense. Route user-facing strings
through whatever centralized message layer the project has, and prefer
structured rendering paths over ad hoc print strings. For judgment on
user-facing text and documentation, see the ux-writing skill.
Testing
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.
- 2d ago First seen · 68 lines · 703 tokens per session scan A 3c2faadf98c1
agents AGENTS.md is an instructions file published in the GitHub repository scarletkc/agents (191 stars, last pushed 6d ago), licensed Apache-2.0. It adds 703 tokens to every session, about $0.0035 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 2026-08-30.
Other instructions, from other repositories
codex-manager 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.
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
ai-driven-development AGENTS.md
Instructions for CodeAlive-AI/ai-driven-development, covering ai-driven development — development guide, git publishing defaults, when to create tags and releases, requires a new tag/release and does not require a new tag/release.
cladding CLAUDE.md
Instructions for qwerfunch/cladding, covering maintainer guide for ai-assisted work on cladding, spec authoring — always hash, never f-nnn, version bumps — use the script, detector additions — count is auto-recomputed and plugin manifest mirrors — built, not hand-authored.
domain-experts AGENTS.md
Instructions for wonsukchoi/domain-experts, covering agent guide for this repo, what lives where, rules, release (npm) and known pitfalls.
SubFrame AGENTS.md
Instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.