Agent skill

CPR Session Resume

by EliaAlberti in EliaAlberti/cpr-compress-preserve-resume

Loads context from recent CPR session logs at the start of a session and can search past sessions by topic, then writes a short resume report.

MITAuto-check passedAgent Workflows

Install CPR Session Resume

skills CLI

$ npx skills add EliaAlberti/cpr-compress-preserve-resume --skill resume -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install EliaAlberti/cpr-compress-preserve-resume resume --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/EliaAlberti/cpr-compress-preserve-resume.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/resume .claude/skills/resume && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "resume" agent skill from https://github.com/EliaAlberti/cpr-compress-preserve-resume/tree/main/skills/resume into .claude/skills/resume/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/EliaAlberti/cpr-compress-preserve-resume/tree/main/skills/resume

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add EliaAlberti/cpr-compress-preserve-resume --skill resume -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install EliaAlberti/cpr-compress-preserve-resume resume --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/EliaAlberti/cpr-compress-preserve-resume.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/resume .agents/skills/resume && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "resume" agent skill from https://github.com/EliaAlberti/cpr-compress-preserve-resume/tree/main/skills/resume into .agents/skills/resume/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add EliaAlberti/cpr-compress-preserve-resume --skill resume -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install EliaAlberti/cpr-compress-preserve-resume resume --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/EliaAlberti/cpr-compress-preserve-resume.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/resume .cursor/skills/resume && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "resume" agent skill from https://github.com/EliaAlberti/cpr-compress-preserve-resume/tree/main/skills/resume into .cursor/skills/resume/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/EliaAlberti/cpr-compress-preserve-resume.git --path skills/resume

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add EliaAlberti/cpr-compress-preserve-resume --skill resume -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install EliaAlberti/cpr-compress-preserve-resume resume --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/EliaAlberti/cpr-compress-preserve-resume.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/resume .gemini/skills/resume && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "resume" agent skill from https://github.com/EliaAlberti/cpr-compress-preserve-resume/tree/main/skills/resume into .gemini/skills/resume/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install EliaAlberti/cpr-compress-preserve-resume resume

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add EliaAlberti/cpr-compress-preserve-resume --skill resume -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/EliaAlberti/cpr-compress-preserve-resume.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/resume .github/skills/resume && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "resume" agent skill from https://github.com/EliaAlberti/cpr-compress-preserve-resume/tree/main/skills/resume into .github/skills/resume/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add EliaAlberti/cpr-compress-preserve-resume --skill resume -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install EliaAlberti/cpr-compress-preserve-resume resume --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/EliaAlberti/cpr-compress-preserve-resume.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/resume .opencode/skills/resume && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "resume" agent skill from https://github.com/EliaAlberti/cpr-compress-preserve-resume/tree/main/skills/resume into .opencode/skills/resume/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: resume
GitHub stars: 514
Token cost: ~623 tokens
SKILL.md length: 176 words
Files: 1
Skills in repo: 3
Repo updated: Sep 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Loads context from recent CPR session logs at the start of a session and can search past sessions by topic, then writes a short resume report.

Starting a new session and catching up on what was done last time
SKILL.md covers Session data and Report
Calls python3
Finding past sessions that dealt with a topic such as authentication

What it does

CPR is a persistent memory plugin for Claude Code that saves, searches and restores conversation context. This skill is the restore side: the /cpr:resume command runs a bundled Python script that collects the project's session logs, so the agent has nothing to open or list, and then writes a report from that data. CLAUDE.md is already in context and is not re-read.

By default it covers the last three sessions. A number after the command, such as 5 or 10, widens that, and a topic word such as auth or migration also searches every log for that term. The report uses a fixed banner format headed by the project name, with one-line bullets that keep exact paths, identifiers and flags from the logs.

If there are no logs yet, it says so in two lines and points to /cpr:compress. If autosaved transcripts are newer than the last curated log, it mentions them once, since they hold the full conversation without a summary. Raw logs are opened only when you ask something the summaries cannot answer.

When your agent uses it

Starting a new session and catching up on what was done last time
Finding past sessions that dealt with a topic such as authentication
Checking whether newer autosaved transcripts exist beyond the last summary

Example prompts

“/cpr:resume 5 to catch up on the last five sessions.”
“/cpr:resume auth to see what we did around authentication.”
“Catch me up on the migration work from the earlier CPR logs.”

Requirements

The CPR plugin installed
Python 3 to run the bundled resume script
Pre-approved tools (allowed-tools): Read, Bash(python3 *)

What it can do on your machine

Read from SKILL.md and the folder at commit cfd1e77. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Read
- Bash(python3 *)
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CPR Session Resume loads about 623 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 176 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~40
When it runs · the whole SKILL.md, loaded when a task matches: ~623

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from EliaAlberti/cpr-compress-preserve-resume at commit cfd1e77, republished under its MIT licence (© EliaAlberti). 176 words, ~623 tokens.

Download SKILL.mdSave it as .claude/skills/resume/SKILL.md (or your agent's skills folder).

name: resume
description: Load context from recent CPR session logs, and search past sessions by topic. Use at the start of a session or when you need to know what happened before.
allowed-tools: Read, Bash(python3 *)
argument-hint: [N] [topic]
disable-model-invocation: true

/cpr:resume

Bring this session up to speed from the project's session logs. The data below was collected by a script, so there is nothing to open or list: read it, then write the report.

Usage: /cpr:resume for the last 3 sessions, /cpr:resume 5 for the last 5, /cpr:resume auth to also search every log for "auth", /cpr:resume 10 migration for both. CLAUDE.md is already in your context; do not re-read it.

Session data

!python3 "${CLAUDE_PLUGIN_ROOT}/scripts/resume_context.py" $ARGUMENTS

Report

Write the report from the data above, in this shape. Keep each bullet to one line, and keep exact values from the logs: paths, identifiers, flags.

══════════════════════════════════════════════
 RESUMING: {project name}
══════════════════════════════════════════════

CONTEXT:
- {what was last worked on}
- {important project state from the logs and CLAUDE.md}

BLOCKERS:
- {from the logs, or "None"}

══════════════════════════════════════════════
 MOST RECENT SESSION: {date time}
 Topic: {topic}
══════════════════════════════════════════════

**Keywords:** {confidence keywords}
**Outcome:** {outcome}

**Key points:**
- {decision, learning or fix}
- {pending task}

══════════════════════════════════════════════
 PREVIOUS SESSIONS ({count})
══════════════════════════════════════════════

- {date}: {topic}, {outcome in a few words}

══════════════════════════════════════════════
 RELATED SESSIONS (topic: "{topic}")      only when a topic was given
══════════════════════════════════════════════

- {date}: {topic}, {why it matched}

══════════════════════════════════════════════
 READY TO:
══════════════════════════════════════════════

- {next step from CLAUDE.md or the latest log}
- {pending task}
══════════════════════════════════════════════

If the data says there are no logs yet, say so in two lines and point to /cpr:compress. If it lists autosaved transcripts newer than the last curated log, mention them once: they hold the full conversation but no summary, and /cpr:resume <topic> searches them.

Read a raw log only when the user asks a question the summaries cannot answer; the summaries exist so that the raw archives never have to be loaded.

Files

Just SKILL.md in skills/resume of EliaAlberti/cpr-compress-preserve-resume.

Open the folder on GitHubat commit cfd1e77

Compare with similar skills

CPR Session Resume next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

CPR Session Resume compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
CPR Session Resume this skillEliaAlberti/cpr-compress-preserve-resume	514	—	~623	Automated safety check: Pass	MIT	1 mo ago
Mindmemos CLImindscale-noah/MindMemOS	1k	—	~3.4k	Automated safety check: Pass	None	10 days ago
File-Based Planning in ArabicOthmanAdi/planning-with-files	27k	—	~3.2k	Automated safety check: Notes	MIT	3 days ago
File-Based Planning in SpanishOthmanAdi/planning-with-files	27k	—	~3.8k	Automated safety check: Notes	MIT	3 days ago
Beads Task Memorygastownhall/beads	28k	—	~1.2k	Automated safety check: Pass	MIT	today
Session History Searchslopus/happy	24k	—	~3.1k	Automated safety check: Pass	MIT	today

Similar skills

Mindmemos CLI
mindscale-noah/MindMemOS
Give an AI agent persistent, cross-session long-term memory through MindMemOS.
1k GitHub stars~3.4k tokensUpdated 10 days ago
Agent WorkflowsAuto-check passed
File-Based Planning in Arabic
OthmanAdi/planning-with-files
Arabic edition of a file-based planning skill that keeps task_plan.md, findings.md and progress.md on disk so multi-step agent work survives lost context.
27k GitHub stars~3.2k tokensUpdated 3 days ago
Agent WorkflowsAuto-check: notes
File-Based Planning in Spanish
OthmanAdi/planning-with-files
Spanish edition of a planning skill that keeps a multi-step agent task on track with task_plan.md, findings.md and progress.md on disk, with recovery after a session reset.
27k GitHub stars~3.8k tokensUpdated 3 days ago
Agent WorkflowsAuto-check: notes
Beads Task Memory
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
28k GitHub stars~1.2k tokensUpdated today
Agent WorkflowsAuto-check passed
Session History Search
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
24k GitHub stars~3.1k tokensUpdated today
Agent WorkflowsAuto-check passed
Mem0 CLI Memory Commands
mem0ai/mem0
Adds, searches, lists, updates and deletes memories on the Mem0 platform from the terminal with the mem0 command, including a JSON mode built for agents.
67k GitHub stars~2k tokensUpdated today
Agent WorkflowsAuto-check: notes

Questions about CPR Session Resume

What does CPR Session Resume do?

Loads context from recent CPR session logs at the start of a session and can search past sessions by topic, then writes a short resume report. CPR is a persistent memory plugin for Claude Code that saves, searches and restores conversation context. This skill is the restore side: the /cpr:resume command runs a bundled Python script that collects the project's session logs, so the agent has nothing to open or list, and then writes a report from that data.

When should I use CPR Session Resume?

CPR Session Resume fits situations like: starting a new session and catching up on what was done last time; finding past sessions that dealt with a topic such as authentication; checking whether newer autosaved transcripts exist beyond the last summary.

How do I install CPR Session Resume in Claude Code?

Run `npx skills add EliaAlberti/cpr-compress-preserve-resume --skill resume -a claude-code`. Or copy the skill folder (skills/resume in EliaAlberti/cpr-compress-preserve-resume) into .claude/skills/resume in your project. Claude Code loads it when a task matches its description.

How do I install CPR Session Resume in Codex?

Run `npx skills add EliaAlberti/cpr-compress-preserve-resume --skill resume -a codex`. Or copy the skill folder (skills/resume in EliaAlberti/cpr-compress-preserve-resume) into .agents/skills/resume in your project. Codex loads it when a task matches its description.

Can I use CPR Session Resume in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add EliaAlberti/cpr-compress-preserve-resume --skill resume -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resume, .gemini/skills/resume, .github/skills/resume and .opencode/skills/resume in your project.

What does CPR Session Resume need to run?

Going by SKILL.md and its folder, CPR Session Resume needs the command-line tools its instructions call (python3). Our summary lists: The CPR plugin installed; Python 3 to run the bundled resume script. Its frontmatter pre-approves these tools: Read, Bash(python3 *).

Does CPR Session Resume access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is CPR Session Resume safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does CPR Session Resume use?

CPR Session Resume is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CPR Session Resume use?

About 623 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to CPR Session Resume?

Skills that share tags, products or a category with CPR Session Resume: Mindmemos CLI (mindscale-noah/MindMemOS, 1k stars), File-Based Planning in Arabic (OthmanAdi/planning-with-files, 27k stars), File-Based Planning in Spanish (OthmanAdi/planning-with-files, 27k stars) and Beads Task Memory (gastownhall/beads, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CPR Session Resume?

EliaAlberti (a GitHub user) maintains it in EliaAlberti/cpr-compress-preserve-resume, which has 514 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 9, 2026.

Source: EliaAlberti/cpr-compress-preserve-resume on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

CPR Session Resume

Install CPR Session Resume

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

/cpr:resume

Session data

Report

Files

Compare with similar skills

Similar skills

Mindmemos CLI

File-Based Planning in Arabic

File-Based Planning in Spanish

Beads Task Memory

Session History Search

Mem0 CLI Memory Commands

More from EliaAlberti/cpr-compress-preserve-resume

CPR Compress

CLAUDE.md Preserve

Questions about CPR Session Resume

Install CPR Session Resume

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

/cpr:resume

Session data

Report

Files

Compare with similar skills

Similar skills

More from EliaAlberti/cpr-compress-preserve-resume

Related

Questions about CPR Session Resume