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 instructions/smcronin/uspto-cli/claude-mdgit clone --depth 1 https://github.com/smcronin/uspto-cliWrote 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/instructions/smcronin/uspto-cli/claude-md)<a href="https://agentmods.dev/instructions/smcronin/uspto-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/smcronin/uspto-cli/claude-md.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 | $0.00831 | $0.00831 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
uspto-cli CLAUDE.md 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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
USPTO CLI - Project Guide
What This Is
Agent-ready CLI for the USPTO Open Data Portal (ODP) API at api.uspto.gov. Built in Go with Cobra.
Architecture
main.go - Entry point
cmd/
root.go - Cobra root command, global flags, error handling
output.go - JSON envelope, NDJSON, CSV, table formatters, facets display
search.go - Patent search with 30+ flags, GET/POST auto-detection, --download
app.go - Application data (18 subcommands including grant XML extraction)
grant.go - Grant XML parsing: claims, citations, abstract, description, fulltext
ptab.go - PTAB proceedings, decisions, docs, appeals, interferences (14 subcommands)
petition.go - Petition decision search/get
bulk.go - Bulk data search/get/files/download
status.go - Status code lookup
summary.go - Compound 5-API-call application summary
family.go - Recursive patent family tree builder
internal/
types/types.go - All API response types, XML structs for grant parsing
api/client.go - HTTP client with rate limiter, 50+ endpoint methods
docs/ - API documentation and analysis
tests/
integration/ - Integration tests (shell out to binary against live API)
Key Conventions
- All commands support
-f json(envelope:{ok, command, pagination, results, facets, version}) - Additional formats:
-f csv,-f ndjson,-f table(default) - API key from
USPTO_API_KEYenv var or--api-keyflag - Rate limiter: sequential requests (burst=1), cross-process file lock, 429 auto-retry (3x, 5s backoff)
--dry-runshows API request without executing (all commands)--minifyfor compact JSON,--quietsuppresses stderr progress--download json|csvfor server-side bulk export (search and PTAB commands)--facetsfor aggregated counts alongside search results- Typed exit codes: 0=OK, 1=general, 2=usage, 3=auth, 4=not-found, 5=rate-limited, 6=server-error
- Application numbers are bare digits (e.g.,
16123456), validated withvalidateAppNumber()
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.
- 4d ago First seen · 71 lines · 831 tokens per session scan A 1d55992458ab
uspto-cli CLAUDE.md is an instructions file published in the GitHub repository smcronin/uspto-cli (39 stars, last pushed 28d ago), licensed MIT. It adds 831 tokens to every session, about $0.0042 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 instructions, from other repositories
rtk CLAUDE.md
Claude Code instructions for rtk-ai/rtk, covering claude.md, project overview, name collision warning, development commands and build & run.
rtk copilot-instructions.md
Copilot instructions for rtk-ai/rtk, covering copilot instructions for rtk, using rtk in this session, instead of: use, build, test & lint and pre-commit gate (must all pass before any pr).
pueue AGENTS.md
AGENTS.md instructions for Nukesor/pueue: This project does not approve of large-scale work done by LLMs.
cs CLAUDE.md
Claude Code instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).
linearis AGENTS.md
AGENTS.md instructions for linearis-oss/linearis, covering agents.md, identity, audience, quick commands and commit rules.
gwm-cli AGENTS.md
AGENTS.md instructions for kbrdn1/gwm-cli, covering gwm-cli — house rules for ai assistants, 🔴 primordial rule — test-driven development is mandatory, the tdd loop (red → green → refactor), what counts as "behaviour" and exceptions (narrow, must be argued in the pr description).