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 Marazii/research-co-pilot --skill vaultgit clone --depth 1 https://github.com/Marazii/research-co-pilotWrote 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/marazii/research-co-pilot/vault)<a href="https://agentmods.dev/skills/marazii/research-co-pilot/vault"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/vault/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/marazii/research-co-pilot/vault"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/vault.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00217 | $0.02939 |
| Opus 5 | $0.00109 | $0.01470 |
| Sonnet 5 | $0.00043 | $0.00588 |
| Haiku 4.5 | $0.00022 | $0.00294 |
Grade A, and why
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 9d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault — the project's home + librarian
You manage the research vault: the clean, visible, templated folder where a research project lives, and the knowledge layer inside it. The vault is two things: an organized project folder (research/<project>/, numbered by lifecycle stage) and a knowledge store (knowledge/). You scaffold it, keep it tidy, serve knowledge on request, and audit for drift.
Read docs/research-vault.md — the canonical spec (the folder template, the stage→folder map, the facts schema, the read/update protocol, the audit checks, the PII hard rule, portability). This skill implements that spec.
Hard rules
- The vault never holds PII.
knowledge/entities.mdstores pseudonyms + non-identifying attributes only;06-data/holds anonymized data only. The real-name key stays off-system. If you ever see a real name / email / phone / address in the vault or about to be written, STOP and flag it. The audit scans for this. - Files are the source of truth; the vault is reconciled. When the vault disagrees with a file, trust the file and correct the vault — never invent an artifact's contents.
- Distinct facts, not overwrites. Two legitimately-different values (recruited N vs analyzed N) are kept as separate keys with notes — never silently overwritten. Only genuine contradictions are flagged.
- The vault is opt-in. If there's no project folder and the user wants a one-off, don't force a vault. Offer to start one.
- Never fabricate knowledge. Record what skills and the user actually established. Don't invent facts, citations, or decisions.
organizeandauditreport or move files — they never edit an artifact's content. Tidying relocates files and updates the manifest/README; fixing drift inside a document is the researcher's call.
Determine the subcommand
Parse $ARGUMENTS; default to show. Find the project folder by looking for a research/<slug>/manifest.json (or the path the user names). If none exists and the subcommand isn't init, say so and offer init.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 180 lines · 217 tokens per session scan A c20d1fc7d272
vault is a skill published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 3mo ago), licensed MIT. It adds 217 tokens to every session and 2,939 once invoked, about $0.0011 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
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
evolving-ai-agents
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
ara-research-manager
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during…
brainstorming-research-ideas
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
creative-thinking-for-research
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
aigc-detector
Academic paper AI content detection, rewriting, and thesis writing assistant. Analyzes text for AI-generated characteristics, provides detailed rewrite suggestions, and generates full thesis drafts. Supports .docx files, outputs reports and rewritten/formatted documents. Bilingual: Chinese & English.