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 protomated/protomated-plugins-official --skill research-memogit clone --depth 1 https://github.com/protomated/protomated-plugins-officialWrote 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/protomated/protomated-plugins-official/research-memo)<a href="https://agentmods.dev/skills/protomated/protomated-plugins-official/research-memo"><img src="https://agentmods.dev/badge/skills/protomated/protomated-plugins-official/research-memo.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 | $0.00115 | $0.02359 |
| Opus 5 | $0.00057 | $0.01179 |
| Sonnet 5 | $0.00023 | $0.00472 |
| Haiku 4.5 | $0.00012 | $0.00236 |
Grade A, and why
research-memo 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 6d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/research-memo — Verified-Source Legal Research Memo Drafter
⚠️ AI-ASSISTED DRAFT — ATTORNEY REVIEW REQUIRED This output was generated by an AI assistant. Every citation must be checked against the original source document before this memo is relied on, filed, or sent. This is not legal advice, and it is not the product of independent legal research — it only reflects the documents you supplied.
Draft a legal research memo that answers your question using only the source documents you've attached to a workspace folder. This skill does not search the open web, does not query any case-law or statute database, and does not fall back on the model's general legal knowledge to fill a citation. If your attached sources don't support part of the answer, that part is flagged as unsupported — never quietly filled in.
This skill only cites what you gave it. It never invents or infers a citation, and it never writes a file without your explicit confirmation.
Why this skill exists
Hallucinated citations are not a hypothetical risk — they are actively producing bar discipline and sanctions for practicing attorneys, including a Ninth Circuit six-month suspension of two immigration attorneys and DOJ sanctions threats against government counsel. Generic AI research tools that draw on open-ended training knowledge or unverified web search invite exactly this failure mode. This skill is built the opposite way: it treats "I don't have a source for that" as a valid and required answer, not a gap to paper over.
Invocation
/research-memo [legal question] — [path to source-document folder]
/research-memo "Does the indemnification clause in the Acme MSA cover third-party IP claims?" — ~/Matters/Acme-Contract/sources
/research-memo "Is the traffic stop supported by reasonable suspicion under these facts?" — ~/Matters/Delgado-Auto-2026/sources
If no folder path is given, ask for one before proceeding. If the attorney names a matter but not a specific sources subfolder, look for a sources/ or research/ folder at the top of that matter, or ask where the source documents live.
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.
- 6d ago First seen · 178 lines · 115 tokens per session scan A b80c7b6f22d5
research-memo is a skill published in the GitHub repository protomated/protomated-plugins-official (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 115 tokens to every session and 2,359 once invoked, about $0.0006 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
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…