read claude web conversation

Other Community

Skill notes

This skill vs. its siblings

Pick by the source you are holding, not by the word "conversation": Source · Use A live claude.ai/chat/… or claude.ai/share/… URL · This skill Local Claude Code sessions (~/.claude/projects/*.jsonl) · claude-code-history-files-finder An already-exported .txt / .json conversation file · claude-export-txt-better

Why the obvious approaches fail (read this first)

Four traps, and every one of them fails silently — you get back something that looks like a complete export, and you only notice the loss if you happen to know how long the conversation really was. Assume you are being lied to by default; the fidelity gate in Step 4 exists to make the lies audible. Login wall. curl and WebFetch don't get an auth redirect — they get a

Step 0 — Choose an injection channel

Three channels can execute JS inside the user's page. They differ only in plumbing, and each fails in its own way, so pick in this order and verify rather than assume. Order · Channel · Use when · Fails when 1 · claude-in-chrome extension · list_connected_browsers returns a browser · Returns [] → the extension's claude.ai login ≠ the Claude Code account. This is structural — retrying, reinstalling, and switch_browser all fail. Move on immediately.

The AppleScript routing trap (read before you blame the user)

AppleScript addresses Chrome by bundle id. If a second Chrome instance is running — chrome-devtools-mcp, puppeteer, playwright, anything launched with its own --user-data-dir — Apple Events can land on that instance instead, and macOS gives you no way to target the first one by pid. There is no workaround. What makes this genuinely dangerous is how it presents: the automation profile

Step 1 — Identify the account case (this decides what you can even get)

How much of the conversation exists for you to fetch depends on whose account the browser is signed into. Establish this early — it is the difference between a complete archive and one with unrecoverable holes, and the user deserves to know which they are getting before you hand it over. Case · Signal · What you can get

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Other
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@daymade · no license declared
Token usage
Heavy
Setup complexity
Guided setup
External API key
Not required
Operating systems
macOS · Windows
Runtime requirements
Python
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
External requests
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

01
Step 0 — Choose an injection channel

Three channels can execute JS inside the user's page. They differ only in plumbing, and each fails in its own way, so pick in this order and verify rather than assume. Order · Channel · Use when · Fails when 1 · claude-in-chrome extension · `list_connected_browsers` returns a browser · Returns `[]` → the extension's claude.ai login ≠ the Claude Code account. This is structural — retrying, reinstalling, and `switch_browser` all fail. Move on immediately.

02
Step 1 — Identify the account case (this decides what you can even get)

How much of the conversation exists for you to fetch depends on whose account the browser is signed into. Establish this early — it is the difference between a complete archive and one with unrecoverable holes, and the user deserves to know which they are getting *before* you hand it over. Case · Signal · What you can get

03
Step 2 — Open the conversation

Extension: `tabs_context_mcp` with `{ "createIfEmpty": true }`, then `navigate`. CDP: `cdp_channel.py open --url <url>` (reuses an existing tab; waits out the Cloudflare interstitial, which the browser clears by itself). Either way, confirm it actually loaded and is logged in — the tab title should be the conversation's name, not "Log in". If you land on a login page, stop and tell

04
Step 3 — Fetch the payload

Always request the full tool rendering. Without `render_all_tools=true` you get placeholders where the analysis was (trap 3 above). Link type · Endpoint `/chat/<conversation-id>` · `GET /api/organizations/<org-uuid>/chat_conversations/<conversation-id>?tree=True&rendering_mode=messages&render_all_tools=true` `/share/<snapshot-id>` · `GET /api/chat_snapshots/<snapshot-id>?rendering_mode=messages&render_all_tools=true`

05
Step 4 — Render locally, through the fidelity gate

This handles both payload shapes (`/chat/` and `/share/`), renders every tool call, folds tool outputs into `<details>`, and collects web_search citations into a "Sources cited" list. It also refuses to write a lossy transcript. Before emitting anything it audits every block — *this block carried N characters; did the renderer emit

06
Step 5 — Paging (extension channel only)

`javascript_tool` truncates large return values. Fetch the `chars` count first, then re-run returning later windows — keep the fetch identical and change only the final expression: Prefer ~14–18k windows; larger risks hitting the limit again. The CDP and AppleScript channels don't need any of this — both return the whole payload on

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.