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/6ixgodd/mine/agents-mdgit clone --depth 1 https://github.com/6ixGODD/mineWhat 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 | $0.02222 | $0.02222 |
| Opus 5 | $0.01111 | $0.01111 |
| Sonnet 5 | $0.00444 | $0.00444 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade A, and why
mine 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Working Agreement
MINE Is Not Everyone's. These are durable, repository-wide agreements. Package-specific schemas, contracts, implementation decisions, and plan details belong in the design knowledge base or the relevant plan, not here.
Source of truth
- Design knowledge base root:
docs/design/index.md(progressive disclosure; indexes orient, leaves specify). - Design ownership marker:
docs/design/.mine-design.toml. - Execution plans:
docs/plan/. - Execution graph machine source:
docs/plan/execution-graph.toml. - Execution graph generated view:
docs/plan/execution-graph.md. - Implementation and review reports:
docs/plan/reports/. - Project configuration:
.mine/config.toml. - Read requirements (
REQUIREMENTS.md) and current implementation evidence before changing design or code.
Design rules
- Separate current implementation, accepted target design, assumptions, local decisions, and unresolved material decisions.
- Do not invent data fields, API behavior, tool names, command flags, or external semantics. Cite repository evidence or mark uncertainty.
- Verify external behavior against opened official or primary documentation and link the exact source in design and plans.
- Follow SOLID at real change boundaries. Do not create speculative interfaces, factories, plugin systems, or indirection without a demonstrated variation or testing boundary.
- Update design before creating a plan that depends on changed design.
- Material architecture decisions require repository-owner approval through the ADR lifecycle before their scope is planning-ready. Agents never infer or fabricate ADR approval; approved decisions are superseded, not reversed in place.
No historical baggage by default
This is a new project unless the user explicitly states otherwise. When a later accepted design conflicts with an earlier internal implementation, change the target implementation directly. Do not keep reserved fields, obsolete parameters, compatibility aliases, dead interfaces, transitional adapters, duplicate schemas, or shims solely to preserve an abandoned plan. If cleanup is too large, create an explicit follow-up plan to remove the obsolete design rather than silently retaining technical debt.
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 · 146 lines · 2,222 tokens per session scan A 84a337917f00
mine AGENTS.md is an instructions file published in the GitHub repository 6ixGODD/mine (17 stars, last pushed 4d ago), licensed MIT. It adds 2,222 tokens to every session, about $0.0111 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
skills-hub AGENTS.md
Instructions for liuxingqitd/skills-hub, covering agents.md, commands, project overview, architecture and 应用结构.
dot-pi AGENTS.md
Instructions for dannote/dot-pi, covering development guidelines, installation, extensions, skills and rules.
cafleet CLAUDE.md
Instructions for himkt/cafleet, covering claude.md, skills, project: cafleet, tech stack and commands.
anycap AGENTS.md
Instructions for anycap-ai/anycap, covering anycap and documentation.
speq-skill CLAUDE.md
Instructions for marconae/speq-skill, covering local development rules, rules and commands.
skillsight CLAUDE.md
Instructions for PackmindHub/skillsight, covering claude.md, commands, architecture, key technical choices and environment.