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/docushell/ethos/agents-mdgit clone --depth 1 https://github.com/docushell/ethosWhat 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 | $0.00295 | $0.00295 |
| Opus 5 | $0.00148 | $0.00148 |
| Sonnet 5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
ethos 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
Agent instructions
Implementing anything in this repository? Start from an explicitly scoped issue, PR, or decider
request. For release-specific work, read the current docs/v<version>-release-prep.md before
writing code. Do not infer a new public surface or workstream from historical planning records.
Other authoritative context, in reading order:
- The scoped issue, PR, or decider request; for a release train, its
docs/v<version>-release-prep.md. docs/execution-status.md— current release state and explicit blockers.README.md+docs/public-boundary-claims.json— approved public wording; never edit claim strings without the approval lane.SPEC.md,docs/determinism-contract.md,docs/decisions/(ADRs) — contracts and decisions.docs/roadmap.md,IMPLEMENTATION_PLAN.md— public direction and historical milestones.
Hard rules that apply to every change: determinism is a contract (byte-identical output under a
pinned profile — add double-run tests for new artifacts); fail closed on missing capability;
claims gate must stay green; no AGPL dependencies; PDFium stays caller-provided unless an
accepted ADR says otherwise; every landed change adds a CHANGELOG.md entry under Unreleased.
Imported Claude Cowork project instructions
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 · 23 lines · 295 tokens per session scan A ea78115c664d
ethos AGENTS.md is an instructions file published in the GitHub repository docushell/ethos (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 295 tokens to every session, about $0.0015 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
Yuxi AGENTS.md
AGENTS.md instructions for xerrors/Yuxi, covering yuxi agent 开发约定, 每次任务先加载什么, 任务与决策, 不能破坏的系统事实 and 证据规则.
ade-cli CLAUDE.md
Instructions for landing-ai/ade-cli, covering ade-cli, agent skills, issue tracker, triage labels and domain docs.
exstruct AGENTS.md
Instructions for harumiWeb/exstruct, covering exstruct ai agents guide, 0. overview, 1. workflow design, 1. use plan mode by default and 2. multi-agent strategy.
talonic-mcp AGENTS.md
Instructions for talonicdev/talonic-mcp, covering ⚠️ #1 footgun: there are two parallel docs surfaces, key domain knowledge: the browser-handoff upload, repo map, quick commands and ci & the publish chain.
talonic-mcp CLAUDE.md
Instructions for talonicdev/talonic-mcp, covering claude.md — claude code entry point for talonic-mcp, ⚠️ before touching docs content — two parallel surfaces, ⚠️ a push to main is a release, quick commands and where to look.
humanities-superpowers AGENTS.md
Instructions for icerain-cmd/humanities-superpowers: For humanities research, scholarly argument, close reading, literature review, citation work, manuscript review, or reviewer response.