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/hidai25/eval-view/agents-mdgit clone --depth 1 https://github.com/hidai25/eval-viewWhat 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 | $0.02634 | $0.02634 |
| Opus 5 | $0.01317 | $0.01317 |
| Sonnet 5 | $0.00527 | $0.00527 |
| Haiku 4.5 | $0.00263 | $0.00263 |
Grade A, and why
eval-view 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 2d 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 — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EvalView Agent Instructions
This file is written for coding agents working inside the EvalView repository. Use it as the fastest way to understand the architecture, the important invariants, and the common extension paths.
For the repo's product and development philosophy, also read:
docs/OPERATING_MODEL.md
What EvalView Is
EvalView is a regression gate for AI agents.
Its core job is:
- Load test cases.
- Execute them against an agent backend.
- Evaluate outputs, tool use, cost, latency, and safety-related checks.
- Save baselines with
snapshot. - Compare current behavior against baselines with
check. - Render reviewable terminal and HTML diffs.
EvalView is not just a scorer. It is opinionated around baseline comparison, regression detection, and developer-facing review flows.
Internally, the intended loop is:
- specify the behavior change
- implement with agent help
- review hard
- run the relevant behavior-tagged slice
- snapshot intentional deltas
- run
check - ship
Core Concepts
TestCase
Path: evalview/core/types.py
TestCase is the declarative input spec. It includes:
- the input prompt or turns
- expected tools and sequences
- thresholds
- optional contains / not_contains / regex / schema checks
- optional per-test adapter and endpoint overrides
If you are changing test-loading or authoring behavior, inspect:
evalview/core/types.pyevalview/core/loader.py
EvaluationResult
Path: evalview/core/types.py
EvaluationResult is the evaluated output of one executed test. It contains:
passedscoreevaluationstrace- timestamps and metadata
This is the main object passed into reports, baselines, and diffing helpers.
GoldenStore
Path: evalview/core/golden.py
GoldenStore persists and loads baselines and variants from .evalview/golden/.
Use it for:
- saving baselines during
snapshot - loading all variants during
check - counting and managing variants
DiffEngine
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.
- 2d ago First seen · 422 lines · 2,634 tokens per session scan A 279ee3f6e0fe
eval-view AGENTS.md is an instructions file published in the GitHub repository hidai25/eval-view (133 stars, last pushed 9d ago), licensed Apache-2.0. It adds 2,634 tokens to every session, about $0.0132 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
evals4j CLAUDE.md
Instructions for dvarahq/evals4j, covering evals4j, layout, build, parity discipline and releasing.
nasde-toolkit CLAUDE.md
Instructions for NoesisVision/nasde-toolkit, covering nasde-toolkit, package structure, how to run, testing and development workflow.
AgentBench-Live CLAUDE.md
Instructions for jackjin1997/AgentBench-Live, covering agentbench-live, project goal, strategy: credibility first, then ride the wave, current sprint scope (accepted from ceo review 2026-03-19) and deferred (todos).
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
TradingAgents-Telegram CLAUDE.md
Instructions for IvanWng97/TradingAgents-Telegram, covering tradingagents-telegram — architecture reference, layout, architecture (for code reviewers), request lifecycle (manual /watch tap) and state ownership.
agent-ship CLAUDE.md
Instructions for Agent-Ship/agent-ship, covering claude.md, project overview, commands, docker development (recommended) and local development (no docker).