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 agents/uipath/coder_eval/claude_codegit clone --depth 1 https://github.com/UiPath/coder_evalWhat 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 | $0.00042 | $0.03424 |
| Opus 5 | $0.00021 | $0.01712 |
| Sonnet 5 | $0.00008 | $0.00685 |
| Haiku 4.5 | $0.00004 | $0.00342 |
Grade A, and why
CLAUDE_CODE 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 yesterday.
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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running Claude Code in Coder Eval
Overview
Claude Code is the default agent in Coder Eval — agent.type: claude-code. It
ships in the base install (no extra needed; the claude-agent-sdk is a core
dependency), and most tasks and tutorials assume it. This guide is the reference
for its config surface, authentication, and telemetry; for the agent-agnostic task
schema see the Task Definition Guide.
Because agent.type defaults to claude-code in experiments/default.yaml, you can
omit the type field entirely.
Setup
Nothing beyond the base install:
uv tool install coder-eval # or: pip install coder-eval
Provide model credentials (see Authentication) and you're ready:
coder-eval run tasks/hello_date.yaml # claude-code is the default
Authentication
Claude Code routing follows the --backend flag (or API_BACKEND env var):
Direct (default)
--backend direct calls the Anthropic API. The SDK picks its own credential, in
order:
ANTHROPIC_API_KEYin the environment /.env, or- a cached
claude login(subscription) session.
No key is validated at startup — the SDK fails with a clear error if none is found.
The llm_judge / agent_judge criteria also need ANTHROPIC_API_KEY under the
direct backend (they call api.anthropic.com).
AWS Bedrock
--backend bedrock routes through Bedrock with bearer-token auth. Set in .env:
| Variable | Purpose |
|---|---|
AWS_BEARER_TOKEN_BEDROCK |
Bedrock bearer token (required) |
AWS_REGION |
Bedrock region, e.g. eu-north-1 (required) |
BEDROCK_MODEL |
Cross-region model id, e.g. eu.anthropic.claude-sonnet-5 (required) |
BEDROCK_SMALL_MODEL |
Small/fast model id (falls back to the main model) |
The agent sets CLAUDE_CODE_USE_BEDROCK=1 and forwards these into the SDK
subprocess. BEDROCK_MODEL is the route-level default; an explicit --model /
-D agent.model=… / task agent.model always wins over it, and bare aliases are
auto-qualified to a regional inference profile (eu. / us. / apac. / global.).
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.
- yesterday First seen · 249 lines · 42 tokens per session scan A d31ecafeacee
CLAUDE_CODE is an agent published in the GitHub repository UiPath/coder_eval (119 stars, last pushed 3d ago), licensed Apache-2.0. It adds 42 tokens to every session and 3,424 once invoked, about $0.0002 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 agents, from other repositories
callbacks
Callbacks provide hooks into the lifecycle of an AnyAgent execution. Using callbacks, you can monitor, control, and extend agent behavior without modifying the core underlying agent logic.
design-interaction
Interaction Designer on the Atlas bench. Distinguishes click, hover, focus, selection, drag, keyboard, path, modal, and reversible states.
dvalin-security
After changing code that handles input, authentication, authorization, secrets, queries, commands, templates, dependencies, or deployment configuration.
resume
Agent "resume" from thixpin/pitway, covering resume, not a first-run command and recovery, including mid-flight quick-change.
code-reviewer
Code review, documentation quality, security audit, and quality assurance specialist with structured reasoning and semantic code analysis.
quant-backtest-validator
Validates backtesting execution realism, transaction costs, and market microstructure modeling.