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/onlyterp/ultracode-shim/agents-mdgit clone --depth 1 https://github.com/OnlyTerp/UltraCode-ShimWrote 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/onlyterp/ultracode-shim/agents-md)<a href="https://agentmods.dev/instructions/onlyterp/ultracode-shim/agents-md"><img src="https://agentmods.dev/badge/instructions/onlyterp/ultracode-shim/agents-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 5.1 | $0.02489 | $0.02489 |
| Opus 5 | $0.01244 | $0.01244 |
| Sonnet 5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade C, and why
UltraCode-Shim AGENTS.md scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/OnlyTerp/UltraCode-Shim/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/OnlyTerp/UltraCode-Shim/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runbook for AI assistants
You are helping a user set up UltraCode-Shim: it lets Claude Code's UltraCode
mode run on any model the user already pays for, chosen from the pre-launch
orchestrator/worker selector or from the /model menu.
Follow these phases in order. Do not skip the doctor. Everything here is pure
Python standard library — do not pip install anything. Prefer the commands
exactly as written; they are cross-platform-aware.
Phase 0 — Understand the goal (read once)
The end state: the user double-clicks "UltraCode (All Models)", picks an
orchestrator + worker in the selector, and Claude Code opens already pointed at
that choice. They can still type /model later and pick any backend they
configured. The mechanism (no magic): a tiny loopback proxy (proxy.py) sits at
ANTHROPIC_BASE_URL, advertises the user's models plus synthesized Worker → X
entries on GET /v1/models, adds the UltraCode envelope to every request, and
routes each pick to its real backend. See docs/HOW_IT_WORKS.md.
Phase 1 — Prerequisites
Run and confirm each:
python3 --version(orpython --version) → must be ≥ 3.8.claude --version→ Claude Code CLI must be installed. If missing:npm i -g @anthropic-ai/claude-code.- Confirm the user has UltraCode access in their Claude plan (they'd have used
/effort ultracodebefore). If not, this project can't grant it.
Phase 2 — Get the code + baseline check
Fastest path — the one-command installer (clones if needed, runs the offline
self-test, creates config.json, and installs a ultracode launcher on PATH):
# mac/linux/WSL
curl -fsSL https://raw.githubusercontent.com/OnlyTerp/UltraCode-Shim/main/install.sh | bash
# windows (PowerShell)
irm https://raw.githubusercontent.com/OnlyTerp/UltraCode-Shim/main/install.ps1 | iex
If you already have a checkout, run ./install.sh (or .\install.ps1) from
inside it. Either way, the installer runs the offline self-test for you.
If you'd rather do it by hand (or the installer can't run):
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 · 190 lines · 2,489 tokens per session scan C 64fa3a2b67ea
UltraCode-Shim AGENTS.md is an instructions file published in the GitHub repository OnlyTerp/UltraCode-Shim (425 stars, last pushed 13d ago), licensed MIT. It adds 2,489 tokens to every session, about $0.0124 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).