What is evidence-check?

A command that checks whether a pull request (PR), a proposed code change for review, includes the required evidence section and supporting artifacts. It validates items such as a claim, verdict, reproduction link, and terminal media.

It is for locally checking PR evidence requirements before pushing a change. The documented checks also cover evidence for user-interface changes and negative test paths.

It catches missing evidence before continuous integration (CI), the automated build and test process, rejects the PR, reducing avoidable review delays.

How jleechanorg/agent-orchestrator-ts configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jleechanorg/agent-orchestrator-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jleechanorg/agent-orchestrator-ts/main/.claude/commands/evidence-check.md

Clone the repo

git clone --depth 1 https://github.com/jleechanorg/agent-orchestrator-ts

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jleechanorg/agent-orchestrator-ts/evidence-check/github.svg)](https://agentmods.dev/commands/jleechanorg/agent-orchestrator-ts/evidence-check)

Your own site

<a href="https://agentmods.dev/commands/jleechanorg/agent-orchestrator-ts/evidence-check"><img src="https://agentmods.dev/badge/commands/jleechanorg/agent-orchestrator-ts/evidence-check/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/jleechanorg/agent-orchestrator-ts/evidence-check"><img src="https://agentmods.dev/badge/commands/jleechanorg/agent-orchestrator-ts/evidence-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 629 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00629
Opus 5.5	$0.00000	$0.00252
Sonnet 5.5	$0.00000	$0.00126
Haiku 4.5	$0.00000	$0.00063

Measured 9d ago against content hash 8b8aeddf16c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evidence-check 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 9d 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.

.claude/commands/evidence-check.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/evidence-check — Validate PR body against Evidence Gate locally

Run this before pushing a PR to catch Evidence Gate failures locally instead of waiting for CI.

Philosophy (jleechanorg fork)

Claims without proof artifacts are insufficient for substantive work. CI checks shape (gist, terminal media + logs, UI or N/A). Reviewers and /er validate substance using docs/evidence/reviewer-checklist.md (video + before/after for UI, claim→artifact map, self-validation, negative paths). Optimize for fast human review and merge confidence.

Usage

/evidence-check [--pr N]

--pr N: PR number to check. If omitted, detects from current branch.

What it checks

The Evidence Gate CI checks (wholesome.yml Evidence Has Media Attachment and evidence-gate.yml Evidence Gate) enforce Evidence Bundle v2 (see CLAUDE.md). Hard requirements:

Evidence section present — PR body must contain ## Evidence (H2 heading)
Claim class + verdict — **Claim class**: ... and **Verdict**: ... (see evidence-gate.yml for valid classes)
Repro gist — **Repro gist**: https://gist.github.com/...
Terminal media — Every PR: **Terminal media**: with HTTPS screenshot/video URL, caption text, and caption references tmux or terminal context
Terminal test output — In addition to terminal media: **Terminal test output**: plus a fenced \``...``` block with real logs mentioning a concrete test command (pnpm, npm, vitest`, …)
UI media — Either **UI media**: with HTTPS screenshot/video + caption, or the exact substring N/A - no UI changes anywhere in ## Evidence

What FAILS the CI check:

Terminal media only (no fenced test logs), or test logs only (no terminal media)
Missing repro gist, missing caption, or caption without tmux/terminal context
Placeholder text (<path>, <value>, TODO, example.com), or simulated output
No Evidence section at all

Read the full file on GitHub · 56 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.

9d ago First seen · 56 lines · 0 tokens per session scan A 8b8aeddf16c7

Subscribe to this mod's changes

evidence-check is a command published in the GitHub repository jleechanorg/agent-orchestrator-ts (8 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 629 tokens. 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 2026-10-02.

Code review Testing

pr-enhance

Command "pr-enhance" from ruvnet/ruflo, covering pr-enhance, usage, options, examples and enhance pr.

ruvnet/ruflo · 0 tokens

audio-pass

Functional audio review for implementation, mix coverage, clarity, and player feedback.

MRCalderon3D/everything-game-dev-code · 15 tokens

test-value-review

Use when a diff adds or changes test files, when a PR claims coverage for config, CI workflows, templates, or HTML output, or when tests look written only to satisfy a "must have tests" rule; not for Playwright selector or performance hygiene (use /playwright-review).

oalders/kitchen-sink · 58 tokens

agent-orchestrator-ts: Command for Claude Code