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/bitcraft-apps/spec-first/agents-mdgit clone --depth 1 https://github.com/bitcraft-apps/spec-firstWhat 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 | $0.00633 | $0.00633 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
spec-first 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Spec First — minimalist development workflow.
Core Philosophy
Build the smallest thing that works. Challenge assumptions. Deliver incrementally.
Principles
- YAGNI: Don't build it until you need it
- KISS: Simplest solution that works
- SRP: Each component does one thing
- MVP First: Deliver narrowest viable change
Anti-Patterns
- Enterprise solutions without justification
- Blind pattern following
- Assumptions without clarification
- Features without immediate need
- Complexity without clear value
Size Constraints
- Agents: 50 lines max
- Skills: 75 lines max
- Workflow scripts: 200 lines max
- Self-documenting through clear naming
Development Checklist
- Can it be smaller? → Make it smaller
- Is it needed now? → If no, skip it
- Does it assume? → Make it ask instead
- Is it complex? → Simplify or remove
- Does it work? → Ship it, iterate later
Documentation Rules
- Minimum viable docs. Document what the user needs to know. If a feature is automatic and invisible, one sentence is enough.
- No duplication. Agent files are the source of truth for agent details. Do not re-list agent names, tools, or descriptions in docs that readers can find in
agents/. - No speculative content. Do not add troubleshooting for problems nobody has reported. Do not document rationale unless the design is surprising.
- Proportional to the change. A one-line config change does not need a new section, glossary entries, ASCII diagrams, or worked examples. Match doc weight to change weight.
- No branding internal mechanics. Do not invent terms for simple concepts. Say what it does plainly.
- User guide = user actions only. If the user doesn't need to do anything, don't explain the internals.
- Technical reference = contract surface. Document interfaces and schemas. Do not duplicate orchestration flows already defined in skill files.
PR Rules
- Every PR must reference a GitHub issue. Use
Closes #<number>in the PR body to auto-close the issue on merge. If no issue exists, create one first.
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 · 65 lines · 633 tokens per session scan A 94abe55dbb14
spec-first AGENTS.md is an instructions file published in the GitHub repository bitcraft-apps/spec-first (4 stars, last pushed 4d ago), licensed MIT. It adds 633 tokens to every session, about $0.0032 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
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
ducklab AGENTS.md
Instructions for jrullan/ducklab, covering working in this repository as an agent and path 1: conventional (edit the tree directly).
Library-First-Engineering copilot-instructions.md
Instructions for StChiotis/Library-First-Engineering: You are an AI agent operating in a Library-First Engineering (LFE) repository. This adapter is a pointer. Canonical rules live in human-readable docs.
harmont-cli CLAUDE.md
Instructions for harmont-dev/harmont-cli, covering testing, documentation, dsl and keep the sdk, hm init templates, and docs in sync.
festival GEMINI.md
Instructions for Obedience-Corp/festival: Festival is a goal-oriented project management methodology for human and AI development workflows, driven by the fest and camp CLIs, installed and kept in sync by a third tool, festival. The skills imported below describe how to plan and execute festivals. Load them when…
story-ui CLAUDE.md
Instructions for southleft/story-ui, covering story ui - ai assistant project guide, what is story ui?, core value proposition, quick reference and important files.