record-replay-skill-reviewer

record-replay-skill-reviewer is a skill for Claude Code, Codex from 45ck/skill-harness. It costs 27 tokens per session (294 once invoked), scanned A, original, MIT.

A review guide for skills created from recordings of browser, desktop, terminal, or app workflows. It checks whether the recorded process is safe, reusable, and free of accidental private data.

In plain words
What is it for?
Use it before installing or sharing a recorded skill to review sensitive data, replace brittle steps, define permissions and failure handling, document verification evidence, and decide where the skill belongs.
Why use it?
Recorded workflows can contain fragile screen coordinates, login details, cookies, local paths, or other session-specific information. The guide separates lasting instructions from those temporary or sensitive details.

Skill for Claude CodeCodex

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

Good fit Use it before installing or sharing a recorded skill to review sensitive data, replace brittle steps, define permissions and failure handling, document verification evidence, and decide where the skill belongs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/45ck/skill-harness/record-replay-skill-reviewer
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 45ck/skill-harness --skill record-replay-skill-reviewer
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

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 record-replay-skill-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/45ck/skill-harness/record-replay-skill-reviewer/github.svg)](https://agentmods.dev/skills/45ck/skill-harness/record-replay-skill-reviewer)
Your own site
<a href="https://agentmods.dev/skills/45ck/skill-harness/record-replay-skill-reviewer"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/record-replay-skill-reviewer/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 record-replay-skill-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/45ck/skill-harness/record-replay-skill-reviewer"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/record-replay-skill-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 294 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 $0.00027 $0.00294
Opus 5 $0.00014 $0.00147
Sonnet 5 $0.00005 $0.00059
Haiku 4.5 $0.00003 $0.00029

Measured 11d ago against content hash 162683ab9b62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

record-replay-skill-reviewer 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 11d 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.

packs/agent-operating-skills/skills/record-replay-skill-reviewer/SKILL.md · 36 lines

What it actually says

Record/Replay Skill Reviewer

Use this skill when a skill is generated from a browser, desktop, terminal, or app recording.

Process

  • Identify what was recorded, who recorded it, when, and which host generated the skill.
  • Separate durable process from incidental UI coordinates, timing, session state, local paths, and private data.
  • Check for credentials, personal data, cookies, account identifiers, tokens, screenshots, private URLs, and unreleased business data.
  • Replace brittle recorded steps with stable tool/API calls when available.
  • Add explicit preconditions, permissions, verification steps, and failure handling.
  • Mark the skill as draft until a human reviews source, redaction, and replay evidence.
  • Decide whether the generated skill belongs as a private repo-local skill, a fixture, or a rewritten first-party skill.

Output

Recording Source

Sensitive Data Review

Durable Workflow

Brittle Steps

Required Redactions

Verification Evidence

Install Decision

Avoid

  • installing generated skills globally by default
  • preserving raw recordings, screenshots, HAR files, cookies, or private traces in the repo
  • confusing a successful replay with a safe reusable skill
  • copying UI-specific steps when an authenticated API or MCP tool is the safer boundary
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. 11d ago First seen · 36 lines · 27 tokens per session scan A 162683ab9b62

Subscribe to this mod's changes

record-replay-skill-reviewer is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 294 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.