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/zwanan-github/agent-template/agents-mdgit clone --depth 1 https://github.com/Zwanan-github/agent-templateWhat 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 | $0.04199 | $0.04199 |
| Opus 5 | $0.02099 | $0.02099 |
| Sonnet 5 | $0.00840 | $0.00840 |
| Haiku 4.5 | $0.00420 | $0.00420 |
Grade A, and why
agent-template 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.
How it starts
The opening of the file, as written. The whole thing — 536 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
This project uses written specs to keep feature work clear, reviewable, and resumable.
Do not rely only on chat history for feature context. Any feature that may span multiple steps, files, or sessions must have its current state saved under specs/features/. Complex, large, unclear, research-heavy, or architecture-heavy work should also save upstream design context under specs/docs/.
Scope
These instructions apply to the entire repository unless a more specific AGENTS.md exists in a subdirectory.
User instructions in the current conversation take priority over this file.
Spec Directory
Feature and Epic specs are stored in:
specs/features/
Design and reference documents are stored under:
specs/docs/
Use this filename format:
YYYY-MM-DD-short-feature-name.md
For large requirements that coordinate multiple child feature specs, use an Epic spec with an -epic suffix when practical:
YYYY-MM-DD-short-epic-name-epic.md
Examples:
2026-05-22-user-login-flow.md
2026-05-22-export-csv.md
2026-05-22-payment-retry-policy.md
2026-05-22-import-workflow-epic.md
Use lowercase words separated by hyphens. Keep names short but recognizable.
Design docs use the same date-prefixed lowercase hyphen format under type-specific directories, for example:
specs/docs/research/2026-05-22-payment-provider-research.md
specs/docs/product/2026-05-22-import-workflow-mvp.md
specs/docs/architecture/2026-05-22-import-workflow-solution.md
specs/docs/design/2026-05-22-import-review-flow.md
specs/docs/decisions/2026-05-22-use-background-import-worker.md
Use specs/docs/ for upstream context and specs/features/ for executable feature/Epic specs, progress, tests, and resume notes.
Agent Workflow Assets
Reusable agent workflow assets are grouped under agent-workflow/:
agent-workflow/guides/ # tutorials, evaluation guide, and tool-specific notes
agent-workflow/skills/ # reusable workflow prompts for common agent tasks
agent-workflow/templates/ # reusable markdown templates
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 · 536 lines · 4,199 tokens per session scan A ad24d0d5ac7f
agent-template AGENTS.md is an instructions file published in the GitHub repository Zwanan-github/agent-template (2 stars, last pushed 1mo ago), licensed MIT. It adds 4,199 tokens to every session, about $0.0210 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 2026-08-31.
Other instructions, from other repositories
sprawling AGENTS.md
Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
hyper-waterfall AGENTS.md
Instructions for postmelee/hyper-waterfall, covering agents.md, 프로젝트 개요, 하이퍼-워터폴 핵심 규칙, 명명 규칙 and 핵심 강제 규칙 (변경 전 매뉴얼 확인 필수).
hyper-waterfall CLAUDE.md
Instructions for postmelee/hyper-waterfall: 본 저장소의 에이전트 운영 규칙은 AGENTS.md를 단일 진실 원천으로 한다. Claude Code도 이 규칙을 그대로 적용한다.
learn-harness-engineering CLAUDE.md
Instructions for walkinglabs/learn-harness-engineering, covering claude.md, project overview, commands, documentation site and run lecture code examples.
trueforge AGENTS.md
Instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.