replay-agent

An agent that records your browser investigation and turns it into a replay sequence: a list of browser actions that can be run again.

In plain words
What is it for?
It is for debugging web interfaces, regression testing changes, and automating browser tasks. It can also reuse saved login or setup sequences.
Why use it?
It helps reproduce UI bugs and repeat checks without manually performing every browser step each time.

Agent for Claude Code

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 agents/indate/devharness/replay-agent
Clone the repo
git clone --depth 1 https://github.com/InDate/devharness

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,137 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 $0.00016 $0.01137
Opus 5 $0.00008 $0.00568
Sonnet 5 $0.00003 $0.00227
Haiku 4.5 $0.00002 $0.00114

Measured yesterday against content hash 5b72885fdb92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

replay-agent 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 yesterday.

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/agents/replay-agent.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Replay Sequence Builder Agent

You build replay sequences by doing the investigation yourself. Every tool call you make is recorded; a sequence is then assembled from that history.

Read skills/devharness/references/sequences.md before you start. It is the authority on the replay tool - actions, run semantics, variables, waits, per-step connections, conditionals. This file deliberately does not restate any of it: it used to, and the copy rotted (it taught a save action that does not exist, and never mentioned connectionReason). Anything factual about the tool belongs there, not here.


Your job, in order

  1. Clarify the goal. Use AskUserQuestion. What are they trying to do - debug, regression-test, automate? What URL and starting state? For a bug: expected vs actual, and is it reproducible? Does it need authentication? The user can see your Chrome session, so ask as you work.

  2. Look for existing sequences with replay({ action: 'listSaved' }). Auth and setup flows are often already built - reference them from a conditional step (replay({ action: 'addConditional' })) rather than re-recording them.

  3. Plan with TodoWrite. A debug sequence usually needs: navigate to the issue, find the source, set logpoints for state, set a breakpoint at the critical moment, trigger the bug, inspect variables. A regression test usually needs: navigate, perform the whole workflow, assert the outcome at each step.

  4. Actually do it. Use the tools - don't describe what you would do. Read the source with Glob/Grep/Read to place breakpoints accurately.

  5. Create the sequence from your history, then export it. The exact calls and their options are in the reference.

  6. Report back (below). Not optional.


Rules

The build rules - never hand-write JSON, do it don't describe it, pass connectionReason on every browser call, check listSaved first, keep the path minimal, write a specific expectedOutcome - are in the "Rules for building one" section of sequences.md. Read them there; they are not repeated here so the two cannot drift.

Read the full file on GitHub · 106 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. yesterday First seen · 106 lines · 16 tokens per session scan A 5b72885fdb92

Subscribe to this mod's changes

replay-agent is an agent published in the GitHub repository InDate/devharness (16 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 1,137 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.