A practical walkthrough of managing Claude Code sessions: resuming with --continue, --resume, and --from-pr, naming sessions, using the session picker, branching to try a different approach, and where transcripts are stored.
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
0
63
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as source-backed.
Metadata reviewed
No reviewed flag detected in metadata.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
No package verification flag provided.
Checksum metadata
No checksum provided for downloaded artifact.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Adoption plan
Current risk score 24/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
No review metadata found; increase manual validation.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
No package verification/checksum metadata.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Missing required evidence: Metadata review. Risk score 31.
Source repository/provenance is listed.
Required in this preset
Review metadata is missing.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is missing.
Optional in this preset
Install payload is available.
Required in this preset
Required gaps: Metadata review
Decision timeline
Blocking gaps: Check metadata review status. Risk 28.
triage
Source/provenance metadata is available.
triage
Review metadata is missing.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is missing.
rollout
Install payload is available.
Blockers: Check metadata review status
Prerequisite readiness
3 prerequisites to line up before setup.
Safety & privacy surface
3 safety and 3 privacy notes across 2 risk areas. Review closely: credentials & tokens.
## Overview
A session is a saved conversation tied to a project directory. Claude Code stores
it locally as you work, so you can resume where you left off, branch to try a
different approach, or switch between tasks. This guide covers the CLI workflow.
## Resume
| Command | What it does |
| --- | --- |
| `claude --continue` | Resume the most recent session in this directory |
| `claude --resume` | Open the session picker |
| `claude --resume <name>` | Resume a named session directly |
| `claude --from-pr <number>` | Resume the session linked to a pull request |
| `/resume` | Switch conversations from inside a session |
Sessions started with `claude -p` or the Agent SDK do not appear in the picker
but can be resumed by passing their session ID to `claude --resume <id>`.
## Name your sessions
Descriptive names make sessions findable and resumable:
- At startup: `claude -n auth-refactor`
- During a session: `/rename auth-refactor`
- From the picker: highlight and press `Ctrl+R`
- On plan accept: the session is named from the plan content unless you already
set a name
## Use the session picker
Run `/resume` (or `claude --resume`) to open the picker. Navigate with arrows,
`Space` to preview, `Ctrl+R` to rename, `Ctrl+A` to widen to all projects,
`Ctrl+W` to widen to all worktrees, and `Ctrl+B` to filter to the current branch.
You can paste a pull/merge request URL to find the session that created it.
## Branch a session
Branching copies the conversation so far and switches you into it, leaving the
original intact:
```text
/branch try-streaming-approach
```
From the command line, combine resume with fork:
```bash
claude --continue --fork-session
```
Forked sessions are grouped under their root in the picker. To return to the
original, resume it by ID or name.
## Manage context within a session
- `/clear` starts fresh with an empty context (the prior conversation is saved).
- `/compact [instructions]` replaces history with a summary.
- `/context` shows what is consuming context.
## Where session data lives
Transcripts are JSONL at `~/.claude/projects/<project>/<session-id>.jsonl`,
removed after 30 days by default (`cleanupPeriodDays`). Use `/export` to copy or
save a readable transcript. Set `CLAUDE_CONFIG_DIR` to relocate storage.
## Source
- Manage sessions: https://code.claude.com/docs/en/sessionsA session is a saved conversation tied to a project directory. Claude Code stores it locally as you work, so you can resume where you left off, branch to try a different approach, or switch between tasks. This guide covers the CLI workflow.
| Command | What it does |
|---|---|
claude --continue |
Resume the most recent session in this directory |
claude --resume |
Open the session picker |
claude --resume <name> |
Resume a named session directly |
claude --from-pr <number> |
Resume the session linked to a pull request |
/resume |
Switch conversations from inside a session |
Sessions started with claude -p or the Agent SDK do not appear in the picker
but can be resumed by passing their session ID to claude --resume <id>.
Descriptive names make sessions findable and resumable:
claude -n auth-refactor/rename auth-refactorCtrl+RRun /resume (or claude --resume) to open the picker. Navigate with arrows,
Space to preview, Ctrl+R to rename, Ctrl+A to widen to all projects,
Ctrl+W to widen to all worktrees, and Ctrl+B to filter to the current branch.
You can paste a pull/merge request URL to find the session that created it.
Branching copies the conversation so far and switches you into it, leaving the original intact:
/branch try-streaming-approach
From the command line, combine resume with fork:
claude --continue --fork-session
Forked sessions are grouped under their root in the picker. To return to the original, resume it by ID or name.
/clear starts fresh with an empty context (the prior conversation is saved)./compact [instructions] replaces history with a summary./context shows what is consuming context.Transcripts are JSONL at ~/.claude/projects/<project>/<session-id>.jsonl,
removed after 30 days by default (cleanupPeriodDays). Use /export to copy or
save a readable transcript. Set CLAUDE_CONFIG_DIR to relocate storage.
Show that Resuming, Branching, and Naming Claude Code Sessions is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/guides/resuming-branching-and-naming-claude-code-sessions)Resuming, Branching, and Naming Claude Code Sessions side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
2 trust signals differ across this comparison (Source provenance, Submitter).
| Field | A practical walkthrough of managing Claude Code sessions: resuming with --continue, --resume, and --from-pr, naming sessions, using the session picker, branching to try a different approach, and where transcripts are stored. Open dossier | Use Claude Code agent view (claude agents) to dispatch, monitor, peek, attach, and organize many background sessions from one terminal with state icons, PR labels, filters, and shell commands for fleet-style multitasking. Open dossier | A practical walkthrough of Claude Code channels: how an MCP-server channel pushes messages, alerts, and webhooks into a running session, how to install and enable Telegram, Discord, or iMessage, sender allowlists, and enterprise controls. Open dossier | Guide to /compact, /memory, and CLAUDE.md hygiene for long Claude Code sessions: when to compact, what to store in memory, and avoiding stale context. Open dossier |
|---|---|---|---|---|
| Next steps | ||||
| Trust | ||||
| Review status | Not reviewed | Not reviewed | Not reviewed | Not reviewed |
| Package trust | Package not verified | Package not verified | Package not verified | Package not verified |
| Source provenanceDiffers | Source-backed | Submission linkedSource submission | Source-backed | Submission linkedSource submission |
| SubmitterDiffers | JPette1783 | kiannidev | JPette1783 | kiannidev |
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | — | — | — |
| Category | guides | guides | guides | guides |
| Source | Source-backed | Source-backed | Source-backed | Source-backed |
| Author | JPette1783 | kiannidev | JPette1783 | kiannidev |
| Added | 2026-06-05 | 2026-06-16 | 2026-06-05 | 2026-06-14 |
| Platforms | ||||
| Harness | ||||
| Source repo | — | — | — | — |
| Safety notes | ✓Branching with /branch or --fork-session copies the conversation but permissions you approved with 'allow for this session' do not carry to the branch; re-approve as needed. Resuming the same session in two terminals without forking interleaves messages into one transcript; fork to keep them separate. Restoring or branching changes session state, not files on disk; use Git for permanent history. | ✓Background sessions run with the permission mode shown in the agent view header; review bypassPermissions and auto modes before dispatching unattended work. Deleting a session from agent view can remove Claude-created worktrees and uncommitted changes—commit or push first. Each dispatched session is a full Claude Code process; do not parallelize destructive tasks on the same checkout without isolation. | ✓Channel input is untrusted external content; treat incoming messages as data, not as instructions that should widen permissions. Events only arrive while the session is open; for unattended use, --dangerously-skip-permissions bypasses prompts and should be used only in trusted environments. Each channel keeps a sender allowlist; only paired/allowlisted IDs can push messages, and anyone who can reply can also approve permission relays if enabled, so allowlist only trusted senders. | ✓Compaction summarizes conversation history; verify summaries before relying on them for security-sensitive or release-critical decisions. Do not store secrets, credentials, or customer identifiers in `/memory` or CLAUDE.md. After compaction, re-validate repository state, test results, and open PR status before continuing destructive edits. |
| Privacy notes | ✓Transcripts are stored locally as JSONL at ~/.claude/projects/<project>/<session-id>.jsonl and removed after 30 days by default (cleanupPeriodDays). Set CLAUDE_CONFIG_DIR to relocate session storage, or CLAUDE_CODE_SKIP_PROMPT_HISTORY to suppress transcript writes. Exported transcripts (/export) contain full messages and tool output; handle them like any sensitive log. | ✓Agent view row summaries are generated by a Haiku-class model from session activity; treat summaries as operational hints, not sanitized exports for public sharing. Sessions started under different project directories appear in the default global list unless you filter with claude agents --cwd. Peek panels and attach mode expose full transcripts that may contain proprietary code, tokens, or customer data. | ✓A channel is an MCP server you configure with your own credentials; tokens are stored locally (for example ~/.claude/channels/telegram/.env). Incoming and outgoing messages pass through the third-party platform (Telegram, Discord, Apple Messages); review what data flows there. The iMessage channel reads your Messages database and requires Full Disk Access; understand that exposure before enabling it. | ✓Memory files persist across sessions and may be committed if stored in project scope. Compaction summaries can retain file paths, issue titles, and internal URLs—review before sharing session exports. Clear memory when offboarding contractors or rotating shared machines. |
| Prerequisites |
|
|
|
|
| Install | — | — | — | — |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.