use-contracts

use-contracts is a skill for Claude Code, Codex from owrede/vault-memory. It costs 186 tokens per session (1,865 once invoked), scanned A, original, MIT.

A way to find and run saved task contracts in vault-memory. A task contract is a repeatable recipe for gathering notes and producing a brief.

In plain words
What is it for?
Use it for meeting preparation, project-status summaries, code-review briefs, or other summaries built from saved notes.
Why use it?
It removes the need to remember which memory tools to call or how to assemble information for common requests.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/owrede/vault-memory/use-contracts
Any agent
npx skills add owrede/vault-memory --skill use-contracts
Clone the repo
git clone --depth 1 https://github.com/owrede/vault-memory

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for use-contracts

README.md
[![agentmods](https://agentmods.dev/badge/skills/owrede/vault-memory/use-contracts.svg)](https://agentmods.dev/skills/owrede/vault-memory/use-contracts)
Your own site
<a href="https://agentmods.dev/skills/owrede/vault-memory/use-contracts"><img src="https://agentmods.dev/badge/skills/owrede/vault-memory/use-contracts.svg" alt="Measured on agentmods" height="20"></a>
Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00186 $0.01865
Opus 5 $0.00093 $0.00932
Sonnet 5 $0.00037 $0.00373
Haiku 4.5 $0.00019 $0.00186

Measured 2d ago against content hash 9ab014ffd856, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use-contracts 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.

skills/use-contracts/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/use-contracts — Discover and run task contracts

vault-memory task contracts are saved, repeatable knowledge-assembly recipes. Each one knows which notes to gather (by link, tag, or search), how to compile them, and where to write the result. The user authored them (or shipped the references); your job is to notice when a request matches one and run it — not to make the user remember tool names or input shapes.

This skill is the missing bridge: the MCP tools list_contracts, describe_contract, and instantiate_contract exist and are discoverable, but nothing tells an agent when to reach for them. This does.

When to invoke

Proactively, when the user's request matches an outcome a contract produces:

  • "prep me for the Acme meeting" / "Briefing fürs Meeting morgen" → likely a meeting-prep-style contract
  • "where does project Atlas stand?" / "Status zu Projekt X" → likely a project-status-style contract
  • "pull together a review brief for this PR" / "Review-Briefing" → likely a code-review-brief-style contract
  • any "compile / summarize / pull together X from my notes" request

Explicitly, when the user says: /use-contracts, "list contracts", "which contracts do I have", "run the … contract", "welche Contracts gibt es", "Contract ausführen".

If you are unsure whether a contract fits, list first (cheap) and check — don't guess.

Requirements

  • mcp__vault-memory__* tools available in the session
  • At least one vault registered; contracts live under _contracts/*.yaml

Workflow

Phase 1 — Discover what exists

Read the contracts Resource for the target vault:

vault-memory://contracts/{vault}

Each entry carries name, description, source/sink counts, and a write_back boolean. This is a pure read — always do it before claiming a contract does or doesn't exist. On a multi-vault setup, resolve {vault} from context or ask which vault.

If no contract matches the user's intent, say so plainly and offer the alternatives (a plain search_hybrid, authoring a new contract with the create-contract skill, or the Obsidian plugin's contract editor). Do not invent a contract.

Read the full file on GitHub · 169 lines

Changes

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.

  1. 2d ago First seen · 169 lines · 186 tokens per session scan A 9ab014ffd856

Subscribe to this mod's changes

use-contracts is a skill published in the GitHub repository owrede/vault-memory (0 stars, last pushed 25d ago), licensed MIT. It adds 186 tokens to every session and 1,865 once invoked, about $0.0009 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.