capturing-proof

A workflow for creating review-ready proof that a mobile app feature works. It produces a video, numbered screenshots, and written files from a rehearsed simulator or emulator flow.

In plain words
What is it for?
Use it to capture a feature demo for a pull request, generate screenshots and a labeled video, save the tested interaction as a Maestro flow, and create proof and pull-request text files.
Why use it?
It avoids recording while still discovering buttons, test IDs, or navigation, which can lead to unclear or failed demos. Reviewers get a repeatable record of the verified feature.

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/lykhoyda/rn-dev-agent/capturing-proof
Any agent
npx skills add Lykhoyda/rn-dev-agent --skill capturing-proof
Clone the repo
git clone --depth 1 https://github.com/Lykhoyda/rn-dev-agent

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,963 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 $0.00105 $0.02963
Opus 5 $0.00053 $0.01482
Sonnet 5 $0.00021 $0.00593
Haiku 4.5 $0.00011 $0.00296

Measured 2d ago against content hash 9b9098ccb4f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capturing-proof 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.

packages/claude-plugin/skills/capturing-proof/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

capturing-proof — Rehearsal-Gated Proof Artifacts for a PR

Produce a permanent proof artifact set for a verified feature: docs/proof/<feature-slug>/ containing a labeled video, numbered screenshots, PROOF.md, PR-BODY.md, and the rehearsed flow persisted as a replayable action.

Core principle. Discovery happens before the camera rolls. The video is the replay of a known-good action — never the LLM working out testIDs or navigation paths on screen. If you would not show the rehearsal pass to a reviewer, do not record it.

What This Produces

  1. Rehearses the flow OFF camera to discover testIDs / navigation / state — recording captures replay, not exploration
  2. Generates a Maestro flow capturing the verified sequence (with M7 metadata)
  3. Starts video recording on the active simulator/emulator
  4. Replays the rehearsed flow via maestro_run (deterministic, hesitation-free)
  5. Captures numbered screenshots at each step
  6. Stops recording and converts to GIF (if ffmpeg available)
  7. Labels the video — adds a text bar below the video with step descriptions (default)
  8. Validates the recording — verifies the feature is actually visible
  9. Writes PROOF.md and generates PR-BODY.md

Protocol

Step 1: Parse arguments and prepare

Establish <feature-slug> (from the command argument, or derive a kebab-case slug from the feature). If ambiguous, ask the user.

mkdir -p docs/proof/<feature-slug>

Step 2: Environment check

Call rn_session(action="status") and require a ready exact session. Then call cdp_status to inspect passive CDP state.

Pre-recording readiness check (GH #8, #9):

  1. If the runtime is not pinned, call rn_session(action="pin_dev_client"). Picker recovery may select only the canonical URL already bound to the session; absence or ambiguity is DEV_CLIENT_ENDPOINT_NOT_FOUND.
  2. Call cdp_navigation_state — verify it returns a valid route name (not empty, not "DevClientLauncher", not "ServerPicker"). If still stuck, ask the user to select the Metro server manually.
  3. Call cdp_dev_settings(action="disableDevMenu") — suppress the shake-to-show dev menu so it doesn't pop up during recording and ruin the video.
  4. Take a baseline screenshot to confirm the starting screen is the actual app, not a system dialog or dev client picker.

Read the full file on GitHub · 284 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. 2d ago First seen · 284 lines · 105 tokens per session scan A 9b9098ccb4f6

Subscribe to this mod's changes

capturing-proof is a skill published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 2,963 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

skill-packager

Authors Agent Skills v1.0 packages (SKILL.md plus references/scripts), runs packageskill to produce a standards-compliant zip, and uses installskill to add skills from HTTPS, registry, workspace, or an uploaded archive. Use when the user wants to turn documentation, workflows, or code into a portable skill, export a…

vixues/LeAgent · 87 tokens

document-processor

Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.

vixues/LeAgent · 44 tokens

workflow-helper

Guidance for creating, managing and executing workflow automations that chain multiple tools and agents together. Use when the user asks about building, listing, running or composing workflows and automated task pipelines.

vixues/LeAgent · 41 tokens

attendance-signin-sheet

Generate printable attendance / 签到表 spreadsheets from name lists. Use when the user asks for 签到表, attendance sheet, meeting sign-in table, or similar printable roster tables (not full payroll attendance scoring unless asked).

vixues/LeAgent · 51 tokens

data-analyzer

Guidance for analyzing structured data, generating statistics and producing data-driven insights. Use when the user asks to analyze data, compute statistics, find patterns, or generate analytical reports.

vixues/LeAgent · 39 tokens

procurement-audit

Review procurement contracts and purchase packages against uploaded compliance rules (招标/采购制度). Use for 采购审核, contract compliance checklists, or procurement statistics rollups.

vixues/LeAgent · 39 tokens