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/zgsm-ai/everything-ai-coding/agents-mdgit clone --depth 1 https://github.com/zgsm-ai/everything-ai-codingWhat 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 | $0.00405 | $0.00405 |
| Opus 5 | $0.00202 | $0.00202 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
everything-ai-coding 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 yesterday.
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.
What it actually says
AGENTS.md
Operating guidance for AI coding agents (Claude Code / Codex / Cursor / Opencode / Costrict / etc.) working in this repo.
Project context
See CLAUDE.md for the architectural overview, commit conventions, test commands, and the data pipeline. Read it before making any non-trivial change.
Do not commit openspec/
openspec/changes/<name>/ is a working directory for proposals, designs, and tasks. It is intentionally ignored (.gitignore:13 openspec/) and should not be pushed to origin/main.
- When you scaffold a change with
/opsx:proposeoropenspec new change, keep the resulting files local. - Do NOT use
git add -f openspec/...to bypass.gitignore. - If you find tracked files under
openspec/onorigin/main, untrack them withgit rm --cachedin a maintenance commit — those are historical leakage from before this rule. - The final spec ends up in code, tests, and
CLAUDE.md. The change folder is a scratchpad, not the source of truth.
Test files
tests/ is also in .gitignore for historical reasons but a large set of files there are tracked (legacy state). When adding new tests:
- For pre-existing tracked test files: edit normally, they pick up changes.
- For brand-new test files: don't force-add — submit them as part of the change description / openspec change directory locally, so reviewers see the test coverage logic without polluting the tracked test surface. Production coverage that must run in CI should live under
ai-resource-eval/tests/instead.
Commit conventions
See CLAUDE.md § 提交规范. TL;DR: [type] 中文描述, single concern per commit, no Co-Authored-By unless explicitly collaborating.
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.
- yesterday First seen · 28 lines · 405 tokens per session scan A d8e94190c512
everything-ai-coding AGENTS.md is an instructions file published in the GitHub repository zgsm-ai/everything-ai-coding (205 stars, last pushed 5d ago), licensed MIT. It adds 405 tokens to every session, about $0.0020 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
aider-desk AGENTS.md
Instructions for hotovo/aider-desk, covering agents.md, common commands, development, type checking and linting and formatting.
Meta_Kim CLAUDE.md
Instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
easy-cheese python.instructions.md
Instructions for paulnsorensen/easy-cheese, covering hard rules, what to flag and what not to flag.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.