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/ifuryst/aifi/agents-mdgit clone --depth 1 https://github.com/iFurySt/aifiWhat 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 | $0.00449 | $0.00449 |
| Opus 5 | $0.00225 | $0.00225 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
aifi 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aifi
This repository is AIFi, an agent-first investment research workspace driven by reusable skills and repository-local research artifacts.
AGENTS.md stays short on purpose. Treat it as a map, not the encyclopedia. Repository-local markdown under docs/ is the system of record.
If a code or workflow change makes a doc stale, update the doc in the same task.
Read At The Start Of Each Task
docs/REPO_COLLAB_GUIDE.md: repository-wide collaboration, commit, documentation, and testing expectations.docs/ARCHITECTURE.md: top-level architecture map and intended package boundaries.docs/design-docs/core-beliefs.md: agent-first operating principles and repository design intent.
Read Before Finishing A Code Change
docs/HISTORY_GUIDE.md: when to record code changes, naming rules, and redaction rules.docs/QUALITY_SCORE.md: current quality targets and gaps by area.
Read When The Task Needs It
docs/PLANS_GUIDE.md: when to create an execution plan and how to maintain it.docs/PRODUCT_SENSE.md: user value, product constraints, and feature prioritization heuristics.docs/RELIABILITY.md: runtime guardrails, observability expectations, and operational readiness.docs/SECURITY.md: secure defaults for research data, source handling, secrets, and external integrations.docs/CICD.md: current CI scope and when to add heavier automation.docs/FRONTEND.md: UI/system guidance if the repo includes a frontend surface.CONTRIBUTING.md: pull request expectations and default review checklist.docs/releases/README.md: how to maintain user-facing release notes.docs/references/README.md: curated external references copied into the repo for agent use.
Working Rules
- Prefer small, explicit, repository-legible abstractions.
- Keep prompts, policies, and architectural rules versioned in-repo.
- For complex work, create an execution plan instead of relying on long chat context.
- Record finished code changes in
docs/histories/.
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 · 39 lines · 449 tokens per session scan A 240bac10f6b9
aifi AGENTS.md is an instructions file published in the GitHub repository iFurySt/aifi (22 stars, last pushed 1mo ago), licensed MIT. It adds 449 tokens to every session, about $0.0022 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
Vibe-Research AGENTS.md
Instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
TradingAgents-astock CLAUDE.md
Claude Code instructions for simonlin1212/TradingAgents-astock, covering tradingagents-astock, 项目概述, 架构, 数据层（v0.2.5 全部直连 http，零第三方数据库依赖） and agent 角色（7 个）.
clawock AGENTS.md
Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.
clawock CLAUDE.md
Instructions for KCNyu/clawock, covering claude.md, identity & user, required reads (every session, in order), what lives where and cron run loop (what openclaw fires).
daily-watchlist CLAUDE.md
Instructions for Benboerba620/daily-watchlist: This file is the source protocol for the Daily Watchlist workflow. Hypothesis Tracker is bundled in this repository as the thesis/evidence layer.
kiasumiles AGENTS.md
Instructions for hosanxiv/kiasumiles, covering project, architecture, commands and agent behavior.