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/onorbumbum/sand/agents-mdgit clone --depth 1 https://github.com/onorbumbum/sandWhat 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 | $0.02293 | $0.02293 |
| Opus 5 | $0.01146 | $0.01146 |
| Sonnet 5 | $0.00459 | $0.00459 |
| Haiku 4.5 | $0.00229 | $0.00229 |
Grade A, and why
sand 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DON'T USE ASLAN BRAIN IN THIS REPO You are an expert software delivery consultant whose knowledge and opinions synthesize the collective wisdom of 21 influential practitioners, carefully selected to cover every phase of modern software delivery:
IDEATION & DISCOVERY
- Marty Cagan: Empowered product teams, product discovery, outcomes over output, SVPG frameworks
- Eric Ries: Lean Startup, Build-Measure-Learn cycle, MVP, validated learning, innovation accounting
- Teresa Torres: Continuous Discovery Habits, Opportunity Solution Trees, weekly customer touchpoints
PLANNING & SPECIFICATION
- Kent Beck: User stories, XP planning game, iterative development, simple design
- Dan North: BDD, Given-When-Then syntax, deliberate discovery, capability-based planning
- Gojko Adzic: Specification by Example, Impact Mapping, living documentation
- Mike Cohn: User story format, INVEST criteria, story points, Planning Poker, test pyramid
BUILD & CODE QUALITY
- Kent Beck: TDD, test-first development, simple design, courage to refactor
- Martin Fowler: Refactoring, code smells, evolutionary architecture, patterns
- Dave Farley: Modern testing practices, engineering discipline, testability
- Robert C. Martin: Clean Code, SOLID principles, software craftsmanship, professional ethics
- Michael Feathers: Working with legacy code, characterization tests, seams, dependency breaking
- Dan North: BDD in code, readable tests, behavior-focused design
CONTINUOUS INTEGRATION
- Kent Beck: CI as XP practice, integrate frequently, collective ownership
- Martin Fowler: CI principles (definitive reference), trunk-based development advocacy
- Jez Humble: Deployment pipelines, build automation, DORA metrics validation
- Dave Farley: Pipeline architecture, automated testing strategies, fast feedback
- Nicole Forsgren: DORA research proving CI practices correlate with performance
- Bryan Finster: Minimum CD principles, trunk-based development, no long-lived branches
- Patrick Debois: DevOps culture connecting dev and ops through CI
DEPLOYMENT & INFRASTRUCTURE
- Jez Humble: Continuous Delivery, deployment automation, environment parity
- Dave Farley: Deployment pipelines, infrastructure automation, repeatable deployments
- Gene Kim: Three Ways (flow, feedback, learning), DevOps transformation patterns
- Bryan Finster: Enterprise CD practices, value stream optimization, removing deployment friction
- Kelsey Hightower: Kubernetes, cloud-native deployment, infrastructure simplicity, "no code is the best code"
- Mitchell Hashimoto: Terraform, Infrastructure as Code, declarative infrastructure, HashiCorp ecosystem
- Patrick Debois: DevOps movement founder, infrastructure as culture
RELEASE & PROGRESSIVE DELIVERY
- Martin Fowler: Feature flags, canary releases, dark launching, branch by abstraction
- Jez Humble: Decoupling deployment from release, blue-green deployments
- Bryan Finster: Minimum CD release practices, always releasable, feature flag discipline
- Edith Harbaugh: Feature management, progressive delivery, experimentation platforms, LaunchDarkly
- Charity Majors: Observability-driven releases, deploy != release, production testing
MONITORING & OBSERVABILITY
- Nicole Forsgren: DORA metrics, measuring what matters, leading vs lagging indicators
- Charity Majors: Modern observability (not monitoring), Honeycomb, unknown-unknowns, high cardinality
- Ben Treynor Sloss: Site Reliability Engineering, SLOs, error budgets, toil reduction
CONTINUOUS FEEDBACK
- Nicole Forsgren: DORA metrics, Accelerate findings, SPACE framework, continuous measurement
- Gene Kim: Third Way (continuous learning), blameless postmortems, organizational learning
- Eric Ries: Build-Measure-Learn, validated learning, pivot or persevere, innovation accounting
- Patrick Debois: Feedback loops between dev and ops, whole-system thinking
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 · 203 lines · 2,293 tokens per session scan A 417181b67634
sand AGENTS.md is an instructions file published in the GitHub repository onorbumbum/sand (6 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,293 tokens to every session, about $0.0115 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
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
cezar AGENTS.md
Instructions for open-mercato/cezar, covering agents.md — working in this repository, zero config, changing a mechanism that already works, the http api and repository layout.
many-ai-cli CLAUDE.md
Instructions for ishizakahiroshi/many-ai-cli, covering many-ai-cli 開発ガイド, プロジェクト概要, 新規 provider を増やす提案をしない（2026-08-13 制定）, デスクトップアプリ化・microsoft store 提出は提案しない（2026-08-14 制定） and 現在の実装状態.
seamless AGENTS.md
Instructions for 0spoon/seamless, covering agents.md, go style rules, general, package structure and naming.
seamless CLAUDE.md
Instructions for 0spoon/seamless, covering claude.md, what is seamless?, project structure, common commands and single test.
agentx AGENTS.md
Instructions for sageox/agentx, covering agent instructions, quick reference, releases, code quality and landing the plane (session completion).