watch

A file-watching mode for EvalView, a tool that checks whether software behavior has regressed after changes. It automatically reruns those checks when selected project files change.

In plain words
What is it for?
Use it during development to monitor source code, tests, configuration, and documentation files. It can run all checks, selected tests, or quicker deterministic checks without the language-model review.
Why use it?
It removes the need to start regression checks manually after every edit. A live result shows pass or fail status, score changes, tool changes, and repeated successes or failures.

Skill for Claude CodeCodex

Part of the eval-view plugin — 7 skills, 2 MCP servers shipped together

Install

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.

agentmods
npx agentmods add skills/hidai25/eval-view/watch
Any agent
npx skills add hidai25/eval-view --skill watch
Clone the repo
git clone --depth 1 https://github.com/hidai25/eval-view

Made for: Claude Code, Codex.

Or install eval-view, the plugin that ships this one along with the rest of its 7 skills, 2 MCP servers.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00555
Opus 5 $0.00009 $0.00278
Sonnet 5 $0.00004 $0.00111
Haiku 4.5 $0.00002 $0.00056

Measured 3d ago against content hash e7a3f0f50ff5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

watch 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.

skills/watch/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watch Mode

Use this skill when the user wants continuous regression monitoring during development. Watch mode observes file changes and automatically re-runs evalview check with debounced triggers.

What this does

EvalView's watch mode uses watchdog to monitor directories for file changes (.py, .yaml, .yml, .json, .md, .txt, .toml, .cfg, .ini). When a change is detected, it runs a regression check via the gate() API and displays a live scorecard with pass/fail status, score deltas, tool changes, and streak tracking.

How to start watch mode

Watch mode is a CLI command (not an MCP tool). Help the user run it:

evalview watch

Common options

  • --quick — Skip LLM judge, deterministic checks only ($0 cost, sub-second)
  • --path src/ --path tests/ — Watch specific directories (default: current directory)
  • --test "my-test" — Only check a specific test by name
  • --test-dir tests/evalview — Path to test cases directory (default: tests)
  • --interval 1 — Debounce interval in seconds (default: 2.0)
  • --fail-on REGRESSION,TOOLS_CHANGED — Comma-separated statuses that count as failure (default: REGRESSION)
  • --sound — Terminal bell on regression

Examples

# Basic: watch everything, full checks
evalview watch

# Fast development loop: no LLM judge, 1-second debounce
evalview watch --quick --interval 1

# Watch specific directories and one test
evalview watch --path src/ --path tests/ --test "calculator-division"

# Strict mode: fail on any behavioral change
evalview watch --fail-on REGRESSION,TOOLS_CHANGED,OUTPUT_CHANGED --sound

Prerequisites

Watch mode requires the watchdog package. If not installed:

pip install evalview[watch]

Notes

  • Watch mode excludes .evalview/, .git/, venv/, node_modules/, __pycache__/, and other common non-source directories automatically.
  • The initial check runs immediately on startup before watching begins.
  • Results include a live scorecard with pass counts, regression counts, health percentage, and streak info.
  • --quick mode is ideal for tight development loops since it costs nothing and runs in sub-second time.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 3d ago First seen · 62 lines · 18 tokens per session scan A e7a3f0f50ff5

Subscribe to this mod's changes

watch is a skill published in the GitHub repository hidai25/eval-view (133 stars, last pushed 10d ago), licensed Apache-2.0. It adds 18 tokens to every session and 555 once invoked, about $0.0001 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.