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 skills/owrede/vault-memory/create-contractnpx skills add owrede/vault-memory --skill create-contractgit clone --depth 1 https://github.com/owrede/vault-memoryWhat 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 | $0.00235 | $0.02904 |
| Opus 5 | $0.00118 | $0.01452 |
| Sonnet 5 | $0.00047 | $0.00581 |
| Haiku 4.5 | $0.00023 | $0.00290 |
Grade A, and why
create-contract 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 yesterday.
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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create-contract — Author a task contract from intent
This skill takes a free-language description of a recurring search/assembly need and
walks it to a validated YAML contract written to the vault's _contracts/
directory. It is the interactive intent → design bridge.
It is the sibling of use-contracts: that skill runs
existing contracts; this one authors new ones. The full DSL reference,
the closed verb enum, the chaining rule, the onboarding gotchas, and a minimal
runnable example all live in
docs/v2/plugin/AUTHORING-CONTRACTS.md —
lean on that document, do not restate it here. This skill is the conversation
that turns intent into a contract that follows it.
When to invoke
Proactively, when the user reveals a recurring knowledge-assembly need:
- "I keep pulling the same notes together before every board meeting."
- "Every time someone joins a project I rebuild the same onboarding dossier."
- "We keep searching for the same risk notes across projects."
- German: "Ich stelle ständig dieselbe Frage zu …", "Wir suchen immer wieder nach …".
The tell is repetition of a question's shape, with one moving part. A one-off
("summarize this single note") is just search_hybrid — not a contract.
Explicitly, when the user says /create-contract, "create / design / author /
build a contract", "neuen Contract erstellen", "Contract entwerfen / bauen".
For discovery, when the user asks "what should I turn into a contract?" or when
use-contracts recently logged no-match gaps (see Discovery mode below).
Contrast with use-contracts: if the user wants to run
a recipe that already exists, that's use-contracts, not this skill.
Requirements
mcp__vault-memory__*tools available in the session- At least one vault registered; contracts live under
_contracts/*.yamland are hot-reloaded by the server (startContractRegistry)
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.
- yesterday First seen · 217 lines · 235 tokens per session scan A 61232c9db5e0
create-contract is a skill published in the GitHub repository owrede/vault-memory (0 stars, last pushed 24d ago), licensed MIT. It adds 235 tokens to every session and 2,904 once invoked, about $0.0012 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…