MemPalace Task Handoff
MemPalace/mempalace
Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.
Lists recent sessions of peer coding agents such as Codex, OpenClaw or Copilot CLI, or your own past sessions, so you can act on their work without copying between terminals.
Install TMA1 Peer Sessions
$ npx skills add tma1-ai/tma1 --skill tma1-peer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tma1-ai/tma1 tma1-peer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tma1-ai/tma1.git skills-src && mkdir -p .claude/skills && cp -r skills-src/claude-plugin/skills/tma1-peer .claude/skills/tma1-peer && rm -rf skills-srcUse ~/.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/
Install the "tma1-peer" agent skill from https://github.com/tma1-ai/tma1/tree/main/claude-plugin/skills/tma1-peer into .claude/skills/tma1-peer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tma1-peer", 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 install https://github.com/tma1-ai/tma1/tree/main/claude-plugin/skills/tma1-peerType 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.
$ npx skills add tma1-ai/tma1 --skill tma1-peer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tma1-ai/tma1 tma1-peer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tma1-ai/tma1.git skills-src && mkdir -p .agents/skills && cp -r skills-src/claude-plugin/skills/tma1-peer .agents/skills/tma1-peer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tma1-peer" agent skill from https://github.com/tma1-ai/tma1/tree/main/claude-plugin/skills/tma1-peer into .agents/skills/tma1-peer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tma1-peer", 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.
$ npx skills add tma1-ai/tma1 --skill tma1-peer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tma1-ai/tma1 tma1-peer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tma1-ai/tma1.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/claude-plugin/skills/tma1-peer .cursor/skills/tma1-peer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "tma1-peer" agent skill from https://github.com/tma1-ai/tma1/tree/main/claude-plugin/skills/tma1-peer into .cursor/skills/tma1-peer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tma1-peer", 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 https://github.com/tma1-ai/tma1.git --path claude-plugin/skills/tma1-peer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tma1-ai/tma1 --skill tma1-peer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tma1-ai/tma1 tma1-peer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tma1-ai/tma1.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/claude-plugin/skills/tma1-peer .gemini/skills/tma1-peer && rm -rf skills-srcUse ~/.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/
Install the "tma1-peer" agent skill from https://github.com/tma1-ai/tma1/tree/main/claude-plugin/skills/tma1-peer into .gemini/skills/tma1-peer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tma1-peer", 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.
$ gh skill install tma1-ai/tma1 tma1-peerInstalls 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).
$ npx skills add tma1-ai/tma1 --skill tma1-peer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tma1-ai/tma1.git skills-src && mkdir -p .github/skills && cp -r skills-src/claude-plugin/skills/tma1-peer .github/skills/tma1-peer && rm -rf skills-srcUse ~/.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/
Install the "tma1-peer" agent skill from https://github.com/tma1-ai/tma1/tree/main/claude-plugin/skills/tma1-peer into .github/skills/tma1-peer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tma1-peer", 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.
$ npx skills add tma1-ai/tma1 --skill tma1-peer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tma1-ai/tma1 tma1-peer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tma1-ai/tma1.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/claude-plugin/skills/tma1-peer .opencode/skills/tma1-peer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "tma1-peer" agent skill from https://github.com/tma1-ai/tma1/tree/main/claude-plugin/skills/tma1-peer into .opencode/skills/tma1-peer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tma1-peer", 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
tma1-peer- GitHub stars
- 119
- Token cost
- ~1.1k tokens
- SKILL.md length
- 464 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Lists recent sessions of peer coding agents such as Codex, OpenClaw or Copilot CLI, or your own past sessions, so you can act on their work without copying between terminals.
- Reading another agent's review feedback without pasting between terminals
- SKILL.md covers Syntax, Flags, Call the tool and Use the response, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Seeing what a peer agent changed on the current project
What it does
The `/tma1-peer` command lists recent sessions on the current project, newest first, and defaults to agents other than you, since the usual reason to call it is to act on a review or change another agent made. Valid names are codex, openclaw, copilot, claude, self, and all, and an unknown name gets a reply listing the valid ones, after which the agent stops without calling the tool. Flags set the detail level, with summary showing the header, tools and files, the default preview showing 3 recent messages, and `--full` showing 40, plus `--limit` for sessions per agent from 1 to 5 and `--since` for the time window, which defaults to 24 hours.
The agent calls `mcp__tma1__get_peer_sessions` with every value you supplied and then reads the response. Each session carries its agent, last activity, duration, tool call count, recent tools and files touched, and a self lookup marks the session you are probably in so your own current work is not reported back as news. The agent leads with the freshest session so you can tell whether the peer work is current, and checks `partial_failures` before treating empty results as silence. The excerpt ends at the rules section.
When your agent uses it
- Reading another agent's review feedback without pasting between terminals
- Seeing what a peer agent changed on the current project
- Recalling your own earlier sessions in this repository
Example prompts
- “What did Codex do on this project in the last two hours?”
- “Show the full conversation of the latest OpenClaw session.”
- “Peer sessions please, with a summary of tools and files touched.”
- “What did I do earlier here? Check my own past sessions.”
Requirements
- The TMA1 MCP server with its get_peer_sessions and get_session_transcript tools
- Pre-approved tools (allowed-tools): mcp__tma1__get_peer_sessions, mcp__tma1__get_session_transcript
What it can do on your machine
Read from SKILL.md and the folder at commit f3dfed8. 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:
mcp__tma1__get_peer_sessionsmcp__tma1__get_session_transcript
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
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
TMA1 Peer Sessions loads about 1.1k tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 464 words of instructions outside code blocks.
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 tma1-ai/tma1 at commit f3dfed8, republished under its Apache-2.0 licence (© tma1-ai). 464 words, ~1,143 tokens.
Download SKILL.mdSave it as
.claude/skills/tma1-peer/SKILL.md (or your agent's skills folder).- name
- tma1-peer
- description
- List recent sessions on this project by agent — peer agents (Codex, OpenClaw, Copilot CLI) or your own past sessions. Invoke when the user wants you to read another agent's review feedback, see what someone else tried, act on cross-agent context, or recall your own earlier work here. Trigger phrases: "what did codex do", "what did openclaw do", "what did copilot do", "peer sessions", "cross-agent context", "what did I do earlier", "我之前在这个项目做了什么", "/tma1-peer".
- allowed-tools
- mcp__tma1__get_peer_sessions, mcp__tma1__get_session_transcript
- argument-hint
- [agent] [--full|--summary] [--limit N] [--since 2h]
TMA1 Peer-Agent Lens
Lists recent sessions on the current project, newest first. Default is peer agents — the ones that aren't you — because the usual reason to call this is "another agent reviewed something, act on it without me copy-pasting between terminals". Naming yourself is also allowed.
Syntax
/tma1-peer # all peers, latest session each
/tma1-peer codex # codex only
/tma1-peer codex --full # codex, with full conversation content
/tma1-peer self # your own recent sessions on this project
/tma1-peer codex --limit 3 # codex, latest 3 sessions
/tma1-peer --summary --limit 5 # all peers, headers only, 5 each
/tma1-peer codex --since 6h # widen the time windowAgent names: codex, openclaw, copilot (= copilot_cli), claude
(= claude_code), self (= you), all / omitted (= every peer but you).
Anything else: reply unknown agent "<X>"; available: codex, openclaw, copilot, claude, self, all
and STOP — do not call the tool with an unrecognised name.
Flags
| Flag | Maps to | Default |
|---|---|---|
--summary | detail: "summary" — header, tools, files; no messages | |
| (none) | detail: "preview" — 3 recent messages per session | default |
--full | detail: "full" — 40 recent messages per session | |
--limit N | limit — sessions per agent, 1-5 | 1 |
--since 2h / --since 90m | since_min in minutes | 1440 (24h) |
Legacy positional form still works: /tma1-peer codex 3 30 means agent
codex, limit: 3, message_limit: 30. A bare leading integer is the
limit, not an agent (/tma1-peer 3 → all peers, limit: 3). Prefer the
flags above when writing new invocations.
Call the tool
mcp__tma1__get_peer_sessions with the parsed agent_source, detail,
limit, since_min. Pass every value the user actually supplied — do
not silently fall back to the defaults.
Use the response
sessions[]—session_id,agent_source,last_activity_ago,duration_minutes,tool_call_count,messages,recent_tool_names,files_touched,cwd. On aselflookup,is_latest_for_cwdmarks the session that is almost certainly the one you're in right now — don't report your own current work back to the user as news.most_recent_session— freshest session's agent + age. Lead with it so the user knows immediately whether the peer work is current.partial_failures—agent → error. Present only when the all-peers fan-out had a failure. Read it before calling empty results silence.note— present only whensessionsis empty and nothing failed.
Show full SKILL.md (173 more words)Show less
Rules:
- Quote what the peer actually said. Do not paraphrase. Reading the peer's exact words is the point of this command.
- Messages are capped per
detail; a cut message carriestruncated: true. Need the rest?mcp__tma1__get_session_transcriptwith thatsession_id. - Empty
sessions, nopartial_failures→ sayno recent <agent> sessions on this project in the windowand stop. Don't fabricate. - Empty
sessionswithpartial_failures→ name the peers that failed and quote the error instead of asserting silence.
Related
- Looking for a session by keyword rather than by agent? Use
/tma1-search. - Already have a
session_id? Go straight toget_session_transcript.
Examples
User: /tma1-peer codex --full
You: (call with agent_source: "codex", detail: "full", limit: 1)
You: "Codex reviewed auth.go 12 min ago and left three concrete issues:
1. ... 2. ... 3. ... Want me to address all three or pick one?"
User: /tma1-peer self --limit 3
You: (call with agent_source: "self", limit: 3)
You: "Three of your sessions here today. The current one aside, the 14:20
session landed the retry fix and the 11:05 one was the failed
migration attempt."
© tma1-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in claude-plugin/skills/tma1-peer of tma1-ai/tma1.
Open the folder on GitHubat commit f3dfed8
Compare with similar skills
TMA1 Peer Sessions 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| TMA1 Peer Sessions this skilltma1-ai/tma1 | 119 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| MemPalace Task HandoffMemPalace/mempalace | 60k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Agent Manager Fleet TUIYoanWai/agent-manager | 582 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Orca CLIstablyai/orca | 89k | 2 repos | ~593 | Automated safety check: Pass | MIT | |
| Paseo Agent Handoffgetpaseo/paseo | 20k | 1 repos | ~606 | Automated safety check: Pass | Custom licence | |
| Codex with ChatGPT Planning LoopXiaoDuoYa/codex-with-chatgpt | 7.2k | — | ~11k | Automated safety check: Notes | MIT |
Similar skills
Agent Manager Fleet TUI
YoanWai/agent-manager
Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked.
Orca CLI
stablyai/orca
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…
Paseo Agent Handoff
getpaseo/paseo
Hands off the current task, including context, decisions and failed attempts, to a fresh agent through Paseo by writing a self-contained briefing prompt and launching that agent.
Codex with ChatGPT Planning Loop
XiaoDuoYa/codex-with-chatgpt
Uses ChatGPT in the browser as the planning and review brain for a Codex session, with Codex keeping all execution and ChatGPT reading the workspace through a bridge.
Memori MCP Memory Usage
MemoriLabs/Memori
Teaches an MCP-connected agent when and how to call Memori's recall, summary, compaction, augmentation, feedback and quota tools to keep context across sessions.
More from tma1-ai/tma1
TMA1 Peer Sessions
tma1-ai/tma1
Lists recent sessions on the current project from other agents such as Claude Code, OpenClaw and Copilot CLI, or from your own earlier work.
TMA1 Session Search
tma1-ai/tma1
Searches past agent sessions on a project by keyword through the TMA1 MCP server and reads back a chosen session so answers can quote it directly.
TMA1 Session Search
tma1-ai/tma1
Searches earlier agent sessions on this project by keyword and reads back a session's conversation, answering with quotes from what was actually said.
TMA1 Observability Query
tma1-ai/tma1
Answers questions about agent spend, token use, traces, events, errors and tool usage by running read-only SQL against a local TMA1 observability store.
Related
Works with
Categories
Questions about TMA1 Peer Sessions
What does TMA1 Peer Sessions do?
Lists recent sessions of peer coding agents such as Codex, OpenClaw or Copilot CLI, or your own past sessions, so you can act on their work without copying between terminals. The `/tma1-peer` command lists recent sessions on the current project, newest first, and defaults to agents other than you, since the usual reason to call it is to act on a review or change another agent made. Valid names are codex, openclaw, copilot, claude, self, and all, and an unknown name gets a reply listing the valid ones, after which the agent stops without calling the tool.
When should I use TMA1 Peer Sessions?
TMA1 Peer Sessions fits situations like: reading another agent's review feedback without pasting between terminals; seeing what a peer agent changed on the current project; recalling your own earlier sessions in this repository.
How do I install TMA1 Peer Sessions in Claude Code?
Run `npx skills add tma1-ai/tma1 --skill tma1-peer -a claude-code`. Or copy the skill folder (claude-plugin/skills/tma1-peer in tma1-ai/tma1) into .claude/skills/tma1-peer in your project. Claude Code loads it when a task matches its description.
How do I install TMA1 Peer Sessions in Codex?
Run `npx skills add tma1-ai/tma1 --skill tma1-peer -a codex`. Or copy the skill folder (claude-plugin/skills/tma1-peer in tma1-ai/tma1) into .agents/skills/tma1-peer in your project. Codex loads it when a task matches its description.
Can I use TMA1 Peer Sessions 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 tma1-ai/tma1 --skill tma1-peer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tma1-peer, .gemini/skills/tma1-peer, .github/skills/tma1-peer and .opencode/skills/tma1-peer in your project.
What does TMA1 Peer Sessions need to run?
SKILL.md names no scripts, command-line tools or credentials: TMA1 Peer Sessions is instructions for the agent only. Our summary lists: The TMA1 MCP server with its get_peer_sessions and get_session_transcript tools. Its frontmatter pre-approves these tools: mcp__tma1__get_peer_sessions, mcp__tma1__get_session_transcript.
Does TMA1 Peer Sessions 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 TMA1 Peer Sessions 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 TMA1 Peer Sessions use?
TMA1 Peer Sessions is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does TMA1 Peer Sessions use?
About 1.1k tokens (SKILL.md is roughly 4.6k 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 TMA1 Peer Sessions?
Skills that share tags, products or a category with TMA1 Peer Sessions: MemPalace Task Handoff (MemPalace/mempalace, 60k stars), Agent Manager Fleet TUI (YoanWai/agent-manager, 582 stars), Orca CLI (stablyai/orca, 89k stars) and Paseo Agent Handoff (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains TMA1 Peer Sessions?
tma1-ai (a GitHub organization) maintains it in tma1-ai/tma1, which has 119 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.
Source: tma1-ai/tma1 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.