collect-evidence

collect-evidence is a skill for Claude Code, Codex from currents-dev/currents-mcp. It costs 117 tokens per session (1,377 once invoked), scanned A, original, Apache-2.0.

A process for proving that an implemented change works by collecting test artifacts from CI, the automated build-and-test environment. Artifacts can include screenshots, videos, traces, GIFs, text, or JSON attachments stored in Currents.

In plain words
What is it for?
Use it to capture before-and-after screenshots, API or command output, multi-step videos, browser traces, and short demos from CI tests.
Why use it?
It provides shareable evidence from a clean test environment instead of relying on a local demonstration. This makes results easier to include in pull requests, tickets, or status updates.

Skill for Claude CodeCodex

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/currents-dev/currents-mcp/collect-evidence
Any agent
npx skills add currents-dev/currents-mcp --skill collect-evidence
Clone the repo
git clone --depth 1 https://github.com/currents-dev/currents-mcp

Made for: Claude Code, Codex.

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.

agentmods badge for collect-evidence

README.md
[![agentmods](https://agentmods.dev/badge/skills/currents-dev/currents-mcp/collect-evidence.svg)](https://agentmods.dev/skills/currents-dev/currents-mcp/collect-evidence)
Your own site
<a href="https://agentmods.dev/skills/currents-dev/currents-mcp/collect-evidence"><img src="https://agentmods.dev/badge/skills/currents-dev/currents-mcp/collect-evidence.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,377 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00117 $0.01377
Opus 5 $0.00059 $0.00688
Sonnet 5 $0.00023 $0.00275
Haiku 4.5 $0.00012 $0.00138

Measured 4d ago against content hash a082c4f6001e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

collect-evidence scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL -o after-order-summary.png "<signed url>"
skills/collect-evidence/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collect Evidence

Show that a change you implemented works, or demo it, by capturing artifacts in CI tests and retrieving them from Currents. The output is a screenshot, video, trace, or attachment to put in a PR, ticket, or status update, plus a dashboard link that does not expire.

Use this when the work is done and someone needs to see it. To debug a test that is failing, use currents-get-context instead.

Do not capture evidence locally: CI runs in a clean, reproducible environment, artifacts are stored and shareable, and this works even without a local browser.

Evidence types and when to use each:

Evidence Use for Captured by
Screenshot Visual state, before/after UI comparison page.screenshot() attached to the test
Text/JSON attachment CLI output, API responses, computed values, diffs testInfo.attach()
Video Multi-step flows, interactions Playwright/Cypress video recording
Trace Full replay with DOM, network, console Playwright tracing
GIF Embedding a short demo in a PR/issue Convert downloaded video with ffmpeg

Requirements

  • The project reports CI test results to Currents (a Currents reporter is configured; runs appear in the dashboard).
  • Currents MCP server connected, or CURRENTS_API_KEY for REST calls to https://api.currents.dev/v1.

Workflow

1. Instrument a test to capture the evidence

Write or extend a test that exercises the change you implemented and captures the artifact at the moment it is visible. See references/instrumentation.md for Playwright and Cypress snippets and reporter configuration.

Rules that make retrieval and pairing work later:

  • Name attachments deterministically (evidence-order-summary.png, not timestamped names). Before/after pairing matches on test title + attachment name.
  • One test per piece of evidence where practical; give the test a distinct, searchable title (e.g. include the word evidence or the feature name).
  • Keep screenshots deterministic: fixed viewport, disable animations, mask dynamic regions.

Read the full file on GitHub · 84 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 84 lines · 117 tokens per session scan A a082c4f6001e

Subscribe to this mod's changes

collect-evidence is a skill published in the GitHub repository currents-dev/currents-mcp (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 117 tokens to every session and 1,377 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories