agent-evidence-capture

agent-evidence-capture is a skill for Claude Code, Codex from xiexie-qiuligao/agent-evidence-mcp. It costs 65 tokens per session (429 once invoked), scanned A, original, MIT.

A process for collecting screenshots, short recordings, and milestone records during long, multi-step computer tasks. The evidence shows what happened at important stages, including errors and the final result.

In plain words
What is it for?
Use it to document starting states, major changes, warnings, failures, retries, and completed outcomes.
Why use it?
It provides a reviewable record when a task involves browser actions, desktop work, testing, troubleshooting, deployment, or administration.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to document starting states, major changes, warnings, failures, retries, and completed outcomes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xiexie-qiuligao/agent-evidence-mcp/agent-evidence-capture
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.

Any agent
npx skills add xiexie-qiuligao/agent-evidence-mcp --skill agent-evidence-capture
Clone the repo
git clone --depth 1 https://github.com/xiexie-qiuligao/agent-evidence-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 agent-evidence-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiexie-qiuligao/agent-evidence-mcp/agent-evidence-capture/github.svg)](https://agentmods.dev/skills/xiexie-qiuligao/agent-evidence-mcp/agent-evidence-capture)
Your own site
<a href="https://agentmods.dev/skills/xiexie-qiuligao/agent-evidence-mcp/agent-evidence-capture"><img src="https://agentmods.dev/badge/skills/xiexie-qiuligao/agent-evidence-mcp/agent-evidence-capture/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.

agentmods 80×15 button for agent-evidence-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiexie-qiuligao/agent-evidence-mcp/agent-evidence-capture"><img src="https://agentmods.dev/badge/skills/xiexie-qiuligao/agent-evidence-mcp/agent-evidence-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 429 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00429
Opus 5 $0.00032 $0.00215
Sonnet 5 $0.00013 $0.00086
Haiku 4.5 $0.00006 $0.00043

Measured 12d ago against content hash bdc246b23051, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-evidence-capture 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 12d 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/agent-evidence-capture/SKILL.md · 69 lines

What it actually says

Task Evidence Capture

Create a session before a long-running task when the user asks for screenshots, recordings, progress evidence, reviewable checkpoints, or a visible audit trail.

Follow This Workflow

  1. Start a session with a task-oriented name.
  2. Capture an initial checkpoint when the starting state matters.
  3. Capture a checkpoint whenever a major state change happens.
  4. Capture an extra checkpoint when an error, warning, or unexpected dialog appears.
  5. Prefer screenshots by default.
  6. Use short recordings only when motion or transient UI behavior matters.
  7. End the session with a summary of artifact paths and key milestones.

Prefer These Labels

Use short, searchable labels:

  • initial-state
  • page-loaded
  • form-filled
  • submitted
  • error-dialog
  • retry-started
  • success
  • final-result

Prefer These Behaviors

Prefer checkpoint capture over raw screenshot capture when the image documents progress.

Avoid repeated screenshots of nearly identical states unless:

  • the user explicitly asks for dense logging
  • the UI changes rapidly and evidence matters
  • a failure sequence needs to be preserved

Store artifacts in the session directory unless the user gives a specific destination.

Include concise reasons with checkpoints so later summaries are readable.

Use Recording Sparingly

Use recording only when:

  • the user explicitly asks for recording
  • drag-and-drop or animation behavior matters
  • a bug cannot be explained with still images
  • the task needs a short demo clip at the end

Prefer short recordings around milestones instead of recording the entire task.

End Cleanly

At the end of the task, report:

  • the session id
  • the artifact directory
  • the most important checkpoints
  • any recording paths that were created
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. 12d ago First seen · 69 lines · 65 tokens per session scan A bdc246b23051

Subscribe to this mod's changes

agent-evidence-capture is a skill published in the GitHub repository xiexie-qiuligao/agent-evidence-mcp (4 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 429 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

blazemeter-api-reference

Comprehensive reference for BlazeMeter REST APIs, including authentication, identifiers, and API endpoints. Use when working with BlazeMeter APIs for (1) Understanding BlazeMeter REST API structure, (2) Authenticating API requests, (3) Obtaining identifiers (Workspace ID, Project ID, Test ID, etc.), (4) Using Test…

Blazemeter/bzm-mcp · 109 tokens

blazemeter-performance-testing

Comprehensive guide for BlazeMeter Performance Testing, including load configuration, reporting, JMeter configuration, Taurus, scenarios, and advanced features. Use when working with Performance tests for (1) Configuring load settings and distribution, (2) Creating and running tests (JMeter, Browser, URL/API…

Blazemeter/bzm-mcp · 138 tokens

blazemeter-administration

Comprehensive guide for BlazeMeter Administration, including workspaces, projects, security, alerts, and team management. Use when working with administration for (1) Managing workspaces and projects, (2) Configuring security settings (SAML SSO, 2FA, API keys), (3) Creating workspace alerts, (4) Managing private…

Blazemeter/bzm-mcp · 111 tokens

blazemeter-getting-started

Getting started guides for BlazeMeter, including onboarding, migration guides, continuous testing journey, glossary, and mobile testing. Use when getting started with BlazeMeter for (1) Navigating BlazeMeter University onboarding, (2) Migrating from Runscope or JMeter, (3) Understanding the continuous testing journey…

Blazemeter/bzm-mcp · 96 tokens

blazemeter-integrations

Comprehensive guide for BlazeMeter Integrations, including APM tools, CI/CD pipelines, and development tools. Use when working with integrations for (1) Integrating APM tools (AppDynamics, Datadog, New Relic, CloudWatch, DX APM, Dynatrace, Delphix), (2) Integrating CI/CD tools (Jenkins, GitHub Actions, GitLab CI/CD…

Blazemeter/bzm-mcp · 131 tokens

blazemeter-private-locations

Comprehensive guide for BlazeMeter Private Locations, including Radar Agent, installation (Docker, Kubernetes, Helm), configuration, management, and troubleshooting. Use when working with Private Locations for (1) Installing agents (Docker, Kubernetes, Helm Chart), (2) Configuring Radar Agent for API Monitoring, (3)…

Blazemeter/bzm-mcp · 103 tokens