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/ssheld/agent-vault/agents-mdgit clone --depth 1 https://github.com/ssheld/agent-vaultWhat 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 | $0.04324 | $0.04324 |
| Opus 5 | $0.02162 | $0.02162 |
| Sonnet 5 | $0.00865 | $0.00865 |
| Haiku 4.5 | $0.00432 | $0.00432 |
Grade A, and why
agent-vault AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- For dynamic execution and shelling out, scrutinize patterns such as `eval`, `new Function`, `child_process.exec`, and `os.system`, especially when inputs are interpolated or not clearly trusted. How it starts
The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository Purpose
This repository is a template source, not project memory.
Template Maintenance Rules
- Keep reusable defaults in
scaffold/agent-vault/. - Do not add project-specific notes or logs to this repository.
- Generate project context only via
scripts/new-project.sh. - When updating generated-project behavior, modify scaffold files and script templates together.
Scope
- These review guidelines apply only when performing pull request code review.
- For generated projects, workflow and handoff behavior is defined in
scaffold/agent-vault/AGENTS.md.
PR Authoring
- For agent-authored pull requests in generated projects, follow
scaffold/agent-vault/AGENTS.mdsectionPR Authoring Standards. - Use
.github/pull_request_template.mdwhen present.
GitHub Post Attribution
- For GitHub issues, issue comments, and non-review PR conversation comments, begin the body with:
> 🤖 **Post by {Model Name}** · via {Client Tool}
- Use your actual model name/version when known. If the exact version is unavailable, use the best identifier you have.
- If the post is specifically PR review feedback or a PR review-feedback response, use the review-policy format instead.
- Never present GitHub posts as if they are the human account owner's personal opinion.
- Prefer repo-relative paths or GitHub links over local filesystem paths in GitHub posts.
Compatibility Note
- Root
AGENTS.mdintentionally inlines review-policy content for Codex compatibility in GitHub review flows. CLAUDE.mdandGEMINI.mdwrappers use@.../review-policy.mdimports.- Do not flag duplication itself; only flag drift between mirrored policy files.
Review Guidelines (for automated code review agents)
When performing a code review on this repository, behave like a senior backend engineer responsible for production reliability, security, maintainability, and operability.
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 · 420 lines · 4,324 tokens per session scan A 7d75d22fc610
agent-vault AGENTS.md is an instructions file published in the GitHub repository ssheld/agent-vault (2 stars, last pushed 1mo ago), licensed MIT. It adds 4,324 tokens to every session, about $0.0216 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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-essentials AGENTS.md
Instructions for ashp15205/vibe-coding-essentials, covering agents.md — vibe coding essentials runtime, identity, mvp context (update daily), active mode and core rules.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).