Borrowing it
Nothing to install: this file belongs to UiPath/coder_eval. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/UiPath/coder_eval/main/CLAUDE.mdgit clone --depth 1 https://github.com/UiPath/coder_evalWrote 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/uipath/coder_eval/claude-md)<a href="https://agentmods.dev/instructions/uipath/coder_eval/claude-md"><img src="https://agentmods.dev/badge/instructions/uipath/coder_eval/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/uipath/coder_eval/claude-md"><img src="https://agentmods.dev/badge/instructions/uipath/coder_eval/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04826 | $0.04826 |
| Opus 5.5 | $0.01930 | $0.01930 |
| Sonnet 5.5 | $0.00965 | $0.00965 |
| Haiku 4.5 | $0.00483 | $0.00483 |
Grade A, and why
coder_eval 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 1mo 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - AI Assistant Guide
Working reference for AI assistants on the coder_eval codebase.
Communication style: use ASD-STE-100 when you speak to the user, and when you edit this file.
Design rationale — why a subsystem is shaped the way it is, and which shipped defect
shaped it — lives under .claude/notes/, which is not auto-loaded; start at
.claude/notes/README.md. Read it before changing grading,
resume, early stop, timing, the reference anti-cheat, or an agent adapter.
User-facing documentation lives in docs/: start with the
User Guide for CLI behaviour and the
Task Definition Guide for task YAML. The full docs
index is generated from the mkdocs.yml nav (see Docs index SSOT below) and is
deliberately not copied here.
Project Overview
coder_eval evaluates AI coding agents with sandboxing, reproducibility, and data-driven analysis.
- Python: >=3.13 · License: Apache 2.0
- Entry point:
coder_eval.cli:app(command:coder-eval)
Directory Structure
src/coder_eval/ — run ls for the current layout. What a filename does not tell you:
models/is the pure-Pydantic layer: the dependency arrow runsagents→models, so it may reachagents/pluginsonly lazily (CE017). All core models import fromcoder_eval.models, never from its submodules.criteria/auto-discovers one checker per type viapkgutil.cli/holds Typer commands; each has a plain-Python twin (CE048).timing.pyowns the single subtraction seam (CE063).argv_match.pyis a STDLIB-ONLY sidecar copied beside the recorder (CE057).fs_permissions.pyisset_permissions, the stacked chmod window.path_utils.pyowns run ids, atomic writes and tree digests — and every run-record filename literal (CE053).models/container_paths.pyownsIN_CONTAINER_ENV(CE056).pricing.pyis the rate SSOT;evalboard/lib/pricing.generated.tsis generated from it bymake pricing-mirror, and CE065 fails the build on drift.reports/is a LEAF rendering layer (markdown, html, experiment, junit + helpers): it may import anywhere, and core may import only its public writers (CE066).reports/html.pyis the evalboard's static twin.result_metrics.pyholdsEvaluationResultmetrics the ORCHESTRATOR reads mid-run;stats.pyis distribution-free statistics, dependency-free by contract;run_record.pyis therun.jsontask-row serializer, not a report.durations.pyisformat_ms, split fromformatting.pyso the reports layer does not reach through an SDK-shaped module for it.isolation/isdriver: docker, one container per task.streaming/is the event protocol andEventCollector.
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.
- 1mo ago Changed · -41 lines · -531 tokens per session fec8681721b3
- 1mo ago Changed · +2 lines · -16,335 tokens per session scan D → A fa4c1b781e93
- 1mo ago Changed · +1,412 tokens per session a24e2d391d56
- 1mo ago Changed · +515 tokens per session abfb5779f0c6
- 1mo ago Changed · +3 lines · +308 tokens per session 1ca8cbc1d11d
- 1mo ago Changed · +17 lines · +8,230 tokens per session scan B → D 670959ca1d92
- 1mo ago Changed · +85 tokens per session 603f0bcc676a
- 1mo ago First seen · 345 lines · 11,142 tokens per session scan B 3a91bf064b45
coder_eval CLAUDE.md is an instructions file published in the GitHub repository UiPath/coder_eval (155 stars, last pushed today), licensed Apache-2.0. It adds 4,826 tokens to every session, about $0.0193 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.