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/holon-run/uxc/agents-mdgit clone --depth 1 https://github.com/holon-run/uxcWhat 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 | $0.00891 | $0.00891 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
uxc AGENTS.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 3d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/main.rs: CLI entrypoint, argument parsing, and command routing.src/lib.rs: public exports and shared crate surface.src/adapters/: protocol implementations (openapi,graphql,grpc,mcp).src/auth/,src/cache/,src/error.rs,src/output.rs,src/protocol.rs: cross-cutting modules.tests/: integration and regression tests (for example,auth_integration_test.rs,cli_help_regression_test.rs).docs/site/: public documentation site content served viamdorigin.docs/: internal notes, release/maintenance docs, and architectural decisions..github/workflows/: CI, lint, build matrix, E2E smoke checks, and docs-site deployment.
Build, Test, and Development Commands
make buildorcargo build --release: build optimized CLI binary.make runorcargo run -- <args>: run locally.make testorcargo test: run test suite.make check: quick validation (cargo check+cargo clippy).make fmtorcargo fmt -- --check: format/check formatting.cargo clippy -- -D warnings: enforce lint cleanliness before PR.npm run docs:dev: preview the docs site locally.npm run docs:index: regenerate directory indexes fordocs/site/.npm run docs:build: build the Cloudflare docs-site bundle.
Coding Style & Naming Conventions
- Use Rust 2021 conventions and
rustfmtdefaults (4-space indentation, no manual alignment tricks). - Naming: files/modules in
snake_case; types/traits inCamelCase; constants inSCREAMING_SNAKE_CASE. - Keep CLI behavior predictable: JSON output envelope is the default contract, text mode is opt-in (
--text). - Prefer small, focused modules; add protocol-specific logic under
src/adapters/<protocol>.rs.
Documentation Guidelines
- Put public product documentation in
docs/site/. Do not add new public-facing docs under top-leveldocs/. - Keep
docs/for internal decision notes, release/maintenance workflows, and architectural records. - Treat
README.mdandREADME.zh-CN.mdas GitHub landing pages; prefer linking user-facing docs tohttps://uxc.holon.run. - Treat
skills/README.mdandhttps://uxc.holon.run/skills/as the browsable skills catalog. - Keep
docs/operations/skills.mdas the skills publish and maintenance log, not as the primary skills directory. - When changing
docs/site/, runnpm run docs:indexandnpm run docs:buildbefore pushing.
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.
- 3d ago First seen · 55 lines · 891 tokens per session scan A 51e3479e1700
uxc AGENTS.md is an instructions file published in the GitHub repository holon-run/uxc (113 stars, last pushed 25d ago), licensed MIT. It adds 891 tokens to every session, about $0.0045 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
api-gateway CLAUDE.md
Instructions for membrane/api-gateway, covering claude.md, working principles, 1. think before coding, 2. simplicity first and 3. surgical changes.
LAP CLAUDE.md
Instructions for Lap-Platform/LAP, covering lap - lean api platform, what this is, quick reference, install and run tests.
data-api-builder copilot-instructions.md
Copilot instructions for Azure/data-api-builder, covering data api builder (dab) - copilot instructions, project overview, key technologies, project structure and building and testing.
grafbase CLAUDE.md
Instructions for grafbase/grafbase, a project described as:
StationAPI AGENTS.md
Instructions for TrainLCD/StationAPI, covering stationapi repository guidelines, project layout, tooling and environment, running and deploying and data management.
caplets AGENTS.md
Instructions for spiritledsoftware/caplets, covering agents.md, commands, package map, agent skills and issue tracker.