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 lightbringer-patents/claude-plugin --skill lightbringer-agent-skillgit clone --depth 1 https://github.com/lightbringer-patents/claude-pluginWrote 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/lightbringer-patents/claude-plugin/lightbringer-agent-skill)<a href="https://agentmods.dev/skills/lightbringer-patents/claude-plugin/lightbringer-agent-skill"><img src="https://agentmods.dev/badge/skills/lightbringer-patents/claude-plugin/lightbringer-agent-skill.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 | $0.00198 | $0.02398 |
| Opus 5 | $0.00099 | $0.01199 |
| Sonnet 5 | $0.00040 | $0.00480 |
| Haiku 4.5 | $0.00020 | $0.00240 |
Grade A, and why
lightbringer-agent-skill 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lightbringer Agent
Route by request:
- A — Patent mining: extract patentable ideas from company data; author, validate, create, refine, submit disclosures.
- B — Report review: comment on a Report shared with the user.
- C — Priority draft review: review a draft application, reply to comments, add feedback, optionally record the formal response.
Comments exist only inside reviews (add_comment/reply_to_comment take a review_id and a quoted anchor), so B and C enter via list_reviews → get_review. Read references/review-workflows.md before any review work.
Workflow A: patent mining
An invention is a problem-solution pair: problems live in customer and operational sources, solutions in engineering sources. Sweep both, then pair.
Autonomy: one checkpoint — the Phase 1 mining brief. After confirmation, run every phase without questions; judgment calls are recorded in the disclosures and final report, never raised in chat. Pause mid-run only if the material is too ambiguous to determine even the technical domain. Create nothing before Phases 1–3 are complete.
Phase 0 — scope and sources
- Sort available connectors: problem-side (support, CRM, product analytics, feedback, incidents, bug reports) and solution-side (code hosts, project trackers, doc stores, engineering chat); some serve both.
- Broad request → propose a concrete scope (projects, repos, folders, time window) in the brief.
- One side missing → plan one-sided mining; note it in the brief and the report.
- Read
references/source-mining.mdbefore harvesting.
Phase 1 — strategy, brief, harvest
Locate the strategy, in order: a document from this session; else search (category: report) for "Intellectual Property Strategy Report" and "Patent Drafting & Prosecution Strategy Report" — if both reports exist read both and state the reading used where they conflict; else use default assumptions (favour detectable infringement and clear technical character). Extract focus areas, priorities, exclusions, jurisdictions.
What ships with it
4 files 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.
- 8d ago First seen · 113 lines · 198 tokens per session scan A 99255053908d
lightbringer-agent-skill is a skill published in the GitHub repository lightbringer-patents/claude-plugin (0 stars, last pushed 1mo ago), licensed MIT. It adds 198 tokens to every session and 2,398 once invoked, about $0.0010 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.
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.
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…
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…