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/wazzamo/vecfs/agents-mdgit clone --depth 1 https://github.com/WazzaMo/vecfsWhat 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 | $0.00555 | $0.00555 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
vecfs 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for VecFS
This document provides essential guidelines for AI agents and LLMs contributing to the VecFS project. It ensures consistency across the codebase, documentation, and overall system architecture.
Code Standards and Design
VecFS follows modern software engineering best practices to ensure the system remains maintainable and extensible.
SOLID Principles
All source code should adhere to the SOLID principles:
- Single Responsibility: Each class or module should have one reason to change.
- Open/Closed: Entities should be open for extension but closed for modification.
- Liskov Substitution: Derived types must be substitutable for their base types.
- Interface Segregation: Clients should not be forced to depend on methods they do not use.
- Dependency Inversion: Depend on abstractions, not concretions.
File Organization
- Source Location: All TypeScript source code must be placed in the
ts-src/directory to accommodate potential multi-language support in the future. - Length: Source files should generally be between 50 and 300 lines.
- Preference: More short, focused files are preferred over fewer large, monolithic ones.
- Naming: Use clear, descriptive names for files and symbols that reflect their specific responsibility.
Documentation and Notes
Documentation is a first-class citizen in VecFS.
Structure
- Core Docs: All primary documentation (requirements, goals, skills) is located in
docs/. - Exploratory Notes: Ideas, research, and implementation plans are stored in
docs/notes/and should be prefixed with the current date (e.g.,YYYY-MM-DD-topic.md).
Formatting Rules
All Markdown files must follow the guidelines in docs/doc-guide.md, specifically:
- Use
#(Level 1 headings) for all new sections, including the document title. - Place an empty line after every heading.
- Use headings instead of bold text for labels or categories.
- Avoid wide tables; use headings and paragraphs for descriptions longer than 60 characters.
- Use
mermaidfor diagrams, ensuring all text labels are quoted.
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 · 56 lines · 555 tokens per session scan A e93c20f98b08
vecfs AGENTS.md is an instructions file published in the GitHub repository WazzaMo/vecfs (9 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 555 tokens to every session, about $0.0028 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
codemem AGENTS.md
Instructions for kunickiaj/codemem, covering codemem, what runs where, commands worth using, gotchas agents usually miss and workflow rules specific to this repo.
memofs AGENTS.md
Instructions for memo-fs/memofs, covering memofs — agent guidelines, monorepo architecture, core behavioral principles and workspace rules.
inquisitor AGENTS.md
AGENTS.md instructions for iamalisson/inquisitor, covering agents.md — inquisitor (always-on), don't classify — probe (depth is an output), delegate before you dig (router first), the gate (objective — only raises depth, never lowers) and confidence check (behavioural, before you act).
mentor AGENTS.md
Instructions for ayhammouda/mentor, covering agents.md, what this is, repository structure, how the artifacts relate and validation.
skill-optimizer GEMINI.md
Instructions for fastxyz/skill-optimizer: @./AGENTS.md @./README.md @./CONTRIBUTING.md @./skills/skill-optimizer/SKILL.md @./skills/skill-optimizer/references/workbench.md.
swift-kmp-skill AGENTS.md
Instructions for sorunokoe/swift-kmp-skill, covering agents.md — swift-kmp, what this repository is, repository structure, how to apply this skill and skill loading order.