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 skills add GuiminChen/crate --skill crate-vaultgit clone --depth 1 https://github.com/GuiminChen/crateWrote 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.
[](https://agentmods.dev/skills/guiminchen/crate/crate-vault)<a href="https://agentmods.dev/skills/guiminchen/crate/crate-vault"><img src="https://agentmods.dev/badge/skills/guiminchen/crate/crate-vault.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.00695 |
| Opus 5 | $0.00028 | $0.00347 |
| Sonnet 5 | $0.00011 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
crate-vault 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 8d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRATE vault agent skill
What CRATE is
CRATE is a local-first toolchain: raw/ holds sources; wiki/ holds compiled Markdown; meta/ holds fingerprints, embeddings DB, and JSON indexes. The CLI is crate (see repo docs/usage.md).
Read first
AGENTS.mdat vault root (if present): project-specific rules.docs/usage.mdin the crate repo: full command reference.docs/providers.md: multi-vendor LLM + embedding (CRATE_LLM_PROVIDER, OpenAI-compatible APIs).meta/wiki_index.json: multi-page wiki graph fromcrate compile --wiki-graph.meta/wiki_body_graph.json: prose link graph fromcrate wiki graph.meta/raw_wiki_coverage.json: optional; fromcrate report raw-wiki --write.
Safe defaults
- Do not bulk-overwrite user wiki pages unless the user asked.
crate wiki-check --applyonly merges whitelist fields on concept pages (related_slugs/conflicts_with_slugsper server implementation); never treat model output as permission to erase bodies.- Prefer
crate wiki promoteto move a vetted answer fromwiki/outputs/intowiki/concepts/.
Command map
| Goal | Command |
|---|---|
| Compile raw → wiki note or multi-page wiki | crate compile / crate compile --wiki-graph |
Watch raw/ |
crate watch (optional --native with watchdog) |
| Q&A | crate ask / crate ask-multi |
| Deterministic link checks | crate lint (add --wikilinks, --orphans, --strict-concepts as needed) |
| Prose link graph JSON | crate wiki graph (--md for wiki/_index/BODYGRAPH.md) |
| Raw coverage report | crate report raw-wiki (--write for JSON under meta/) |
| Session-scoped compile | List paths in .crate/ingest_session.md then crate ingest |
| Extended notes index | crate wiki index-extend → meta/wiki_index_extended.json |
| Semantic wiki audit | crate wiki-check (optional --apply-dry-run / --apply) |
| HTTP URL check (opt-in) | crate lint --http-external (set SKIP_HTTP_LINT=1 to skip) |
| Diagnostics | crate doctor |
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.
- 8d ago First seen · 49 lines · 56 tokens per session scan A 9c405bde1ad4
crate-vault is a skill published in the GitHub repository GuiminChen/crate (16 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 695 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.