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/learnaihubc/agentrules/agents-mdgit clone --depth 1 https://github.com/LearnAIHubC/AgentRulesWhat 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 | $0.01280 | $0.01280 |
| Opus 5 | $0.00640 | $0.00640 |
| Sonnet 5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
AgentRules 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
- Turn the request into 2-5 concrete, verifiable acceptance criteria.
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
3. Preserve Existing Architecture and Framework Boundaries
Understand the system before extending it. Preserve the guarantees already in place.
When creating or extending a project:
- If a codebase, scaffold, template, architecture, dependency set, or framework has already been selected, inspect its structure, conventions, dependency graph, existing patterns, and supported extension points before designing or coding.
- Prefer the project's established abstractions and integration paths when they cover the need. Do not introduce a parallel architecture or replace or bypass a dependency or framework without explicit justification.
- Keep feature logic modular, but integrate it through the lifecycle and control boundaries of the adopted architecture and frameworks, such as dependency injection, routing, state management, persistence, middleware, and configuration.
- Do not make a feature work by bypassing those boundaries in a way that disables framework hooks, guarantees, cross-cutting behavior, or existing functionality.
- If the requirement does not fit the current boundaries, explain the mismatch and tradeoffs before changing the architecture or introducing or replacing dependencies.
- Verify the feature through the project's normal entry points and regression tests, confirming that the existing architecture and framework behavior remains effective.
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 · 115 lines · 1,280 tokens per session scan A f0f88d9d0b6e
AgentRules AGENTS.md is an instructions file published in the GitHub repository LearnAIHubC/AgentRules (17 stars, last pushed 20d ago), licensed MIT. It adds 1,280 tokens to every session, about $0.0064 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
concord-mcp CLAUDE.md
Instructions for Get-Concord-AI/concord-mcp, covering concord mcp — engineering guide, what this project is, coding rules (non-negotiable), the "never typecast" pattern for db rows and external json and architecture.
repository-harness AGENTS.md
Instructions for hoangnb24/repository-harness, covering agent instructions and harness.
repository-harness CLAUDE.md
Instructions for hoangnb24/repository-harness, covering project rules and harness.
boring-is-all-you-need AGENTS.md
Instructions for Khalilzhang0825/boring-is-all-you-need, covering agents.md - boring is all you need codex guide, project intent, working rules, validation and release discipline.
AGENTS.md AGENTS.md
Instructions for Anbeeld/AGENTS.md, covering global instructions, priorities, boundaries, uncertainty and evidence.
paceflow CLAUDE.md
Instructions for paceaitian/paceflow, covering claude.md, 维护规则, 常用验证, 一条命令聚合全部核心套件 + claude plugin validate + git diff --check and 任一子套件非零退出即整体非零退出,杜绝手敲漏跑某套件致回归静默漏网.