What is Claude-Replay CLAUDE.md?

A set of instructions for working on Claude Replay, a tool that records Claude Code session events in a database so they can be searched, analyzed, compared, or visualized. It also defines the project's boundaries and architecture.

Use it before changing Claude Replay, especially when adding search, session analytics, session comparison, dashboards, terminal views, or structured exports.

It helps coding agents understand what the repository already does and prevents them from rebuilding features that Claude Code already provides.

How constripacity/Claude-Replay configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to constripacity/Claude-Replay. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/constripacity/Claude-Replay/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/constripacity/Claude-Replay

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/constripacity/claude-replay/claude-md/github.svg)](https://agentmods.dev/instructions/constripacity/claude-replay/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/constripacity/claude-replay/claude-md"><img src="https://agentmods.dev/badge/instructions/constripacity/claude-replay/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/constripacity/claude-replay/claude-md"><img src="https://agentmods.dev/badge/instructions/constripacity/claude-replay/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 810 This file is loaded in full into every session.

When invoked 810 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00810	$0.00810
Opus 5.5	$0.00324	$0.00324
Sonnet 5.5	$0.00162	$0.00162
Haiku 4.5	$0.00081	$0.00081

Measured 2mo ago against content hash 290dbccba147, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Claude-Replay CLAUDE.md 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 2mo 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.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Replay — context for Claude Code

What this repo is

Observability layer for Claude Code sessions — the cross-project search / analytics / visualization that complements native resume/rewind (it does NOT re-implement them; see the positioning note below). Hooks silently into every session, stores events + checkpoints in SQLite, exposes 10 MCP tools. Sibling to Claude Bridge under Constripacity.

Positioning (load-bearing — read before adding features)

Native Claude Code already does resume (--continue/--resume), rewind (/rewind), and plaintext /export. Replay must NOT duplicate those. Build only in the differentiated lane: full-text search, per-session analytics (metrics.py / classify.py), session diff, and visualization (dashboard/TUI/ structured export). Filter every new feature through "does native already do this?"

Architecture in one sentence

Passive hooks write to SQLite. MCP tools read from SQLite. Dashboard + TUI visualize SQLite. Nothing else.

Port

8766 (Bridge is 8765 — deliberately different)

Key files

claude_replay/store.py — all DB access lives here, nowhere else
claude_replay/hooks.py — hook handlers, dispatched by claude-replay hook <type>
claude_replay/resume.py — resume brief generation (death cause + live git state)
claude_replay/classify.py — death-cause classification (pure, no DB access)
claude_replay/metrics.py — per-session insight metrics (pure, no DB access)
claude_replay/doctor.py — doctor self-check (pure evaluate(); CLI gathers facts)
claude_replay/analytics.py — cross-session rollup (pure aggregate(), no DB access)
claude_replay/export.py — trace rendering (html / json / md)
claude_replay/server.py — Starlette app (MCP SSE + JSON API + static)
claude_replay/tui_client.py — async httpx client over the JSON API (testable, no Textual)
claude_replay/tui.py — Textual session browser (talks to a running serve, never the DB)
claude_replay/cli.py — all CLI subcommands

Read the full file on GitHub · 67 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.

2mo ago First seen · 67 lines · 810 tokens per session scan A 290dbccba147

Subscribe to this mod's changes

Claude-Replay CLAUDE.md is an instructions file published in the GitHub repository constripacity/Claude-Replay (1 stars, last pushed 2mo ago), licensed MIT. It adds 810 tokens to every session, about $0.0032 per session on Opus 5.5. 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.

Claude-Replay CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Claude-Replay CLAUDE.mdconstripacity/Claude-Replay	Instructions file	1	2mo ago	MIT	A	810	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Claude-Replay: Instructions file for Claude Code