Git History Bug Audit
ben-manes/caffeine
Audits a module by walking its git history commit by commit, tracking unresolved issues forward, and reporting the ones that survive to HEAD as findings.
Orchestrate full-duplex coding agent sessions via ACPX (preferred) or tmux (fallback), composing OpenClaw native tools and community Skills.
$ npx skills add LeoYeAI/openclaw-master-skills --skill conduxt -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills conduxt --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/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/conduxt .claude/skills/conduxt && 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 "conduxt" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/conduxt into .claude/skills/conduxt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conduxt", 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/LeoYeAI/openclaw-master-skills/tree/main/skills/conduxtType 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 LeoYeAI/openclaw-master-skills --skill conduxt -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills conduxt --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/conduxt .agents/skills/conduxt && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "conduxt" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/conduxt into .agents/skills/conduxt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conduxt", 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 LeoYeAI/openclaw-master-skills --skill conduxt -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills conduxt --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/conduxt .cursor/skills/conduxt && 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 "conduxt" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/conduxt into .cursor/skills/conduxt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conduxt", 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/LeoYeAI/openclaw-master-skills.git --path skills/conduxt--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 LeoYeAI/openclaw-master-skills --skill conduxt -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills conduxt --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/conduxt .gemini/skills/conduxt && 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 "conduxt" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/conduxt into .gemini/skills/conduxt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conduxt", 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 LeoYeAI/openclaw-master-skills conduxtInstalls 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 LeoYeAI/openclaw-master-skills --skill conduxt -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/conduxt .github/skills/conduxt && 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 "conduxt" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/conduxt into .github/skills/conduxt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conduxt", 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 LeoYeAI/openclaw-master-skills --skill conduxt -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills conduxt --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/conduxt .opencode/skills/conduxt && 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 "conduxt" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/conduxt into .opencode/skills/conduxt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conduxt", 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.
conduxtOrchestrate full-duplex coding agent sessions via ACPX (preferred) or tmux (fallback), composing OpenClaw native tools and community Skills.
Conduxt is an agent skill from LeoYeAI/openclaw-master-skills. Orchestrate full-duplex coding agent sessions via ACPX (preferred) or tmux (fallback), composing OpenClaw native tools and community Skills. Handles any coding task: requirements, bug fixes, refactoring, investigations. Use when: "implement feature X", "fix this bug", "refactor the API layer", "start agent", "open a session", "code this", "fix issue N".
Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts (for example `_meta.json`, `scripts/launch.sh` and `scripts/setup.sh`).
It sits in Development, covering Refactoring and Debugging. It works with tmux. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 3 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
gitghnpxgeminiFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, gh and npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Conduxt loads about 4.9k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 1,522 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.
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); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,522 words, ~4,930 tokens.
.claude/skills/conduxt/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.You are the orchestrator. Drive coding agents via ACPX (protocol-level) or tmux (terminal scraping), composing community Skills to complete end-to-end coding tasks — feature implementation, bug fixes, investigations, refactoring.
You are the OpenClaw Main model. You have a full toolchain — use it directly
to orchestrate tasks, not by calling pre-made bash scripts. Scripts in the
scripts/ directory exist only as optional helpers.
This Skill supports two agent communication backends. Prefer ACPX, use tmux as fallback.
| Dimension | ACPX (Protocol) | tmux (Terminal Scraping) |
|---|---|---|
| Communication | Full-duplex JSON-RPC over stdio | Half-duplex PTY scraping |
| Output | Typed ndjson (tool_call/text/done) | Raw ANSI text (burns 30-40% Context) |
| Mid-task instructions | Prompt queue: submit anytime, queued | send-keys: timing issues, may be treated as user input |
| Completion detection | Native [done] signal | Regex matching or Callback injection |
| Cancellation | Cooperative session/cancel (preserves state) | C-c (unreliable, may corrupt state) |
| Crash recovery | Auto-restart + load serialized session | Session survives but agent death goes unnoticed |
| Permissions | --approve-all / --deny-all policy-based | Interactive TTY popups (block unattended flows) |
| Visual monitoring | ndjson pipe to external tools | tmux split-pane (advantage) |
ACPX is strictly superior for communication, observation, and mid-task instructions. tmux only wins on maturity and visual monitoring.
| Scenario | Backend |
|---|---|
| Default / new tasks | ACPX |
| ACPX unavailable or unstable | tmux (fallback) |
| Need visual split-pane monitoring | tmux (or ACPX + external dashboard) |
| Agent doesn't support ACP | tmux |
| Tool | Purpose | Key Usage |
|---|---|---|
exec | Run shell commands | acpx prompt, tmux send-keys, git worktree, gh |
exec pty:true | Interactive terminal | Simple one-off tasks (do NOT nest tmux inside PTY) |
process | Background processes | background:true for long tasks, process action:log limit:20 |
read/write/edit | File operations | MEMORY.md, active-tasks.json |
gh | GitHub CLI | gh issue view, gh pr create |
git | Version control | git worktree add/remove, git branch, git push |
| Command | Purpose |
|---|---|
acpx prompt -s <session> "<instruction>" | Send prompt (creates session if new, appends if existing) |
acpx prompt -s <session> --no-wait "<msg>" | Fire-and-forget (returns immediately) |
acpx prompt -s <session> --format json "<msg>" | Structured ndjson output |
acpx sessions list | List all active sessions |
acpx sessions show -s <session> | Show session details |
acpx cancel -s <session> | Cooperative cancel of current task |
acpx prompt -s <session> --approve-all "<msg>" | Auto-approve all permission requests |
| Skill | When to Use | Core Capability |
|---|---|---|
coding-agent | Agent lifecycle management (tmux backend) | tmux session + Callback wakeup + worktree |
tmux | Low-level tmux operations | Socket management, send-keys, wait-for-text |
tmux-agents | Multi-agent types (tmux backend) | Codex, Gemini, local models |
gemini | Gemini CLI coding | Long-context tasks |
resilient-coding-agent | Gateway restart recovery | tmux session persistence |
Composition principle: Use Skills when available (they encapsulate best practices). Fall back to native tools when Skills don't cover your needs. coding-agent / tmux-agents use tmux backend — if using ACPX backend, use
acpxcommands directly.
User ←→ You (Main) ←→ acpx ←→ ACP Adapter ←→ Coding Agent
↕ ↕
MEMORY.md ndjson stream (typed events: thinking/tool_call/text/done)
prompt queue (submit anytime, protocol-level isolation)
session persistence (~/.acpx/sessions/*.json)acpx prompt -s <session> "<instruction>" enters the prompt queue[done] event in ndjson stream → you are woken up → notify userUser ←→ You (Main) ←→ tmux session ←→ Coding Agent
↕ ↕
MEMORY.md send-keys (inject instructions)
capture-pane (read output)
Callback event (completion notification)tmux send-keys -t <session> "<text>" EnterEscape first and wait for idle.Each scenario provides both ACPX (preferred) and tmux (fallback) paths.
Triggers (task source is flexible):
1. Understand the Task
Task sources are diverse — handle flexibly:
• User describes requirement → use description text as prompt directly
• Link to external doc/wiki → fetch content and extract requirements
• GitHub issue → exec: gh issue view <N> --json title,body
• Code review comments → extract action items
2. Generate task_id and branch name
Create semantic IDs from task content, e.g.:
• "add pagination" → task_id: add-pagination, branch: feat/add-pagination
• "perf issue" → task_id: perf-analysis, branch: fix/perf-analysis
• issue #78 → task_id: issue-78, branch: fix/issue-78
3. Create isolated workspace
→ exec: git worktree add ../worktrees/<task_id> -b <branch> main
4. Start Coding Agent
┌─ ACPX path (preferred) ────────────────────────────────────┐
│ exec: cd ../worktrees/<task_id> && acpx prompt \ │
│ -s <task_id> \ │
│ --approve-all \ │
│ --no-wait \ │
│ "<task description + callback instructions (see §6)>" │
│ │
│ • --no-wait: returns immediately, doesn't block you │
│ • --approve-all: auto-approve permissions for unattended │
│ • session auto-persisted to ~/.acpx/sessions/<task_id>.json│
└────────────────────────────────────────────────────────────┘
┌─ tmux path (fallback) ─────────────────────────────────────┐
│ a) Use coding-agent Skill (recommended) │
│ b) Use tmux-agents Skill (for Gemini/Codex) │
│ c) Direct exec: │
│ tmux new-session -d -s <task_id> -c ../worktrees/<id> │
│ tmux send-keys -t <task_id> "claude" Enter │
│ tmux send-keys -t <task_id> "<prompt + callback>" Enter │
└────────────────────────────────────────────────────────────┘
5. Write MEMORY.md task entry (see §7)
6. Inform user
→ "Session <task_id> started, agent is working. Will notify on completion."
7. Wait for completion
ACPX: [done] in ndjson stream → read result → route
tmux: Callback arrives or 30min timeout → capture-pane → notifyParallel tasks: Repeat the above for each task. ACPX natively supports named parallel sessions.
Before creating PRs, check for file conflicts between branches with git diff --name-only.
Trigger: "Start a session for API refactoring"
ACPX:
exec: acpx prompt -s api-refactor "You are my coding assistant, await instructions."
→ Creates named session, agent enters wait state
tmux:
exec: tmux new-session -d -s api-refactor -c /path/to/repo
exec: tmux send-keys -t api-refactor "claude" Enter
Report to user:
"Session api-refactor started. You can:
• 'Tell api-refactor to start with interface definitions'
• 'How is api-refactor doing?'
• 'Stop api-refactor'"Trigger: "Tell <session> to do Y" / "Change <session>'s direction"
ACPX (no timing issues, protocol-level isolation):
Append instruction: acpx prompt -s <session> --no-wait "Focus on interface definitions, skip DB layer"
Cancel current: acpx cancel -s <session>
tmux (watch for timing):
Append instruction: tmux send-keys -t <session> "Focus on interface definitions" Enter
Interrupt current: tmux send-keys -t <session> Escape
Force stop: tmux send-keys -t <session> C-cTrigger: "How is <session> doing?" / "status"
ACPX:
exec: acpx sessions show -s <session>
→ Structured session state, no ANSI stripping needed
→ Or use --format json for recent ndjson events
tmux:
exec: tmux capture-pane -p -t <session> -S -20
→ Strip ANSI: sed 's/\x1b\[[0-9;]*[a-zA-Z]//g'
→ Summarize for user (don't paste raw terminal output)
List all sessions:
ACPX: acpx sessions list
tmux: tmux list-sessions| Condition | Recommended Agent | ACPX Launch | tmux Launch |
|---|---|---|---|
| Default / best coding | Claude Code | acpx prompt -s X --agent claude | coding-agent Skill |
| Long context needed | Gemini CLI | acpx prompt -s X --agent gemini | gemini Skill |
| Need Codex | Codex CLI | acpx prompt -s X --agent codex | tmux-agents Skill |
| Simple one-off | Direct exec | No session needed | exec pty:true |
ACPX-supported agent adapters:
npx @zed-industries/claude-agent-acp (adapter)npx @zed-industries/codex-acp (adapter)gemini --experimental-acp (native support)Trigger: [done] signal or Callback shows completed + tests pass
1. Independently verify tests (don't trust agent's self-report)
→ cd <worktree> && <auto-detect test runner>
2. Push branch
→ git push -u origin <branch>
3. Create PR
→ gh pr create --title "fix: <title>" --body "..." --base main --head <branch>
4. Update MEMORY.md: status=completed, add PR link
5. Notify userACPX:
End session (history preserved in ~/.acpx/sessions/)
→ No need to kill processes, ACPX manages lifecycle
tmux:
tmux kill-session -t <session>
Common:
git worktree remove <dir> --force
git branch -d <branch> (optional)
Edit MEMORY.md: status → abandoned or completedACPX ndjson stream natively provides [done] signals, but we still inject the
Callback JSON instruction for unified processing logic. The JSON can be extracted
directly from the ndjson stream — no regex matching against terminal output.
Requires injection and detection of callback-json keyword via capture-pane.
Append to the end of the agent prompt:
When you complete this task, you MUST output the following JSON block
wrapped in triple backticks with language tag "callback-json":
{
"task_id": "<task_id>",
"status": "completed|failed|need_clarification",
"branch": "<branch>",
"files_changed": ["file1.go", "file2_test.go"],
"test_results": { "passed": 42, "failed": 0, "skipped": 1 },
"duration_minutes": 12,
"summary": "Brief description of what was done"
}
Commit your code and run tests BEFORE outputting this JSON. This is mandatory.| Condition | Your Action |
|---|---|
completed + failed=0 | Independently verify tests → create PR → notify user |
completed + failed>0 | Append instruction: "N tests failing, please fix and re-output callback" |
failed | Update MEMORY.md → notify user of failure reason |
need_clarification | Forward summary to user, wait for reply, then send to agent |
Pure if/else — no LLM interpretation of natural language needed.
| Method | ACPX | tmux |
|---|---|---|
| Primary | ndjson [done] signal | coding-agent Skill built-in Callback |
| Fallback | Extract callback-json from ndjson | capture-pane regex matching |
| Background | N/A (stream is continuous) | scripts/watchdog.sh |
## In-Flight Tasks
### add-pagination: Implement pagination for /api/users
- **Status**: in-progress
- **Branch**: feat/add-pagination
- **Session**: add-pagination
- **Backend**: ACPX | tmux
- **Agent**: Claude Code | Gemini CLI
- **Started**: 2026-03-10T14:30:00Z
- **Latest Milestone**: 14:42 - Running tests
- **Callback**: pending| Event | Action |
|---|---|
| Task created | Add entry, status=pending |
| Agent started | status → in-progress, record backend type |
| User asks for progress | Update Latest Milestone |
| Completion signal received | status → completed/failed |
| PR created | Add PR link |
| Cleanup | status → completed/abandoned |
MEMORY.md must be written under any backend — it is the only shared state across sessions and agents. ACPX session history is per-agent and does not share across sessions.
ACPX has built-in crash recovery — auto-restarts agent and loads serialized session. You only need to check if the session is still active:
acpx sessions list # check if session exists
acpx sessions show -s <session> # check detailed statusIf session disappeared (ACPX itself crashed), recover context from MEMORY.md and recreate.
tmux session survives but agent may have died:
tmux has-session -t <session> 2>/dev/null # is session alive
tmux capture-pane -p -t <session> -S -1 # any outputOptional: scripts/watchdog.sh background loop (zero token).
Three scripts in scripts/ with dual-backend support. You can use them but don't have to:
| Script | Purpose |
|---|---|
setup.sh <task_id> <branch> <worktree_dir> [task_desc] [backend] | Create branch + worktree + initialize MEMORY.md |
launch.sh <task_id> <worktree_dir> <prompt_file> [backend] [agent] | ACPX-first agent launch with auto tmux fallback |
watchdog.sh [task_id] | Background zero-token monitoring (ACPX/tmux aware) |
Parameters:
backend: acpx (default if available) | tmux | autoagent: claude | gemini | codex | aider | auto| Action | Command |
|---|---|
| Send prompt | acpx prompt -s <name> "<text>" |
| Fire-and-forget | acpx prompt -s <name> --no-wait "<text>" |
| Structured output | acpx prompt -s <name> --format json "<text>" |
| Auto-approve perms | acpx prompt -s <name> --approve-all "<text>" |
| List sessions | acpx sessions list |
| Show session | acpx sessions show -s <name> |
| Cancel task | acpx cancel -s <name> |
| Action | Command |
|---|---|
| Create session | tmux new-session -d -s <name> -c <dir> |
| Send instruction | tmux send-keys -t <name> "<text>" Enter |
| Read output | tmux capture-pane -p -t <name> -S -30 |
| List sessions | tmux list-sessions |
| Send interrupt | tmux send-keys -t <name> C-c |
| Kill session | tmux kill-session -t <name> |
| Action | Command |
|---|---|
| Fetch issue | gh issue view <N> --json title,body,labels |
| Create worktree | git worktree add <dir> -b <branch> main |
| Remove worktree | git worktree remove <dir> |
| Push branch | git push -u origin <branch> |
| Create PR | gh pr create --title "..." --body "..." --base main --head <branch> |
| Skill | Backend | Your Usage |
|---|---|---|
coding-agent | tmux | Preferred agent launch for tmux fallback |
tmux | tmux | Low-level operations (custom socket, wait-for-text) |
tmux-agents | tmux | Multi-agent types (Codex, Gemini, local models) |
gemini | tmux | Gemini CLI for long-context tasks |
resilient-coding-agent | tmux | Gateway restart recovery |
When using ACPX backend, these tmux-based Skills don't apply. Use
acpxcommands directly. When ACPX is unavailable, fall back to these Skills.
Phase 1 (Current): ACPX and tmux in parallel
• New tasks prefer ACPX
• ACPX instability → tmux fallback
• Validate ACPX session persistence and crash recovery
Phase 2: High-value migration
• Migrate half-duplex and context-pollution-heavy scenarios to ACPX
• tmux demoted to visual monitoring only
Phase 3 (End state): ACPX as primary path
• tmux optional (visual only)
• ACPX becomes the standard interface for all agent communicationexec pty:true (double PTY allocation)Escape first and wait for idle before appending-S -20, ACPX use --format json pipe--approve-all for unattended; --approve-reads when security matters| User Says | What You Do |
|---|---|
| "Implement feature X for project Y" | Scenario A: understand requirement → create task → start agent |
| "Investigate this performance issue" | Scenario A: analyze problem → create investigation task |
| "Do these three tasks in parallel" | Scenario A × N (parallel named sessions) |
| "Fix issue #78" (optional) | Scenario A: fetch issue description |
| "Start a session for X" | Scenario B: interactive |
"Tell <session> to do Y" | Scenario C: acpx prompt / tmux send-keys |
"How is <session> doing?" | Scenario D: acpx sessions show / capture-pane |
| "Use Gemini for this task" | Scenario E: acpx --agent gemini / gemini Skill |
| "Create PR" | Scenario F |
"Stop <session>" / "cleanup" | Scenario G |
| "status" | List all sessions + MEMORY.md in-flight tasks |
"retry <task>" | Scenario G cleanup + Scenario A restart |
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files (scripts) in skills/conduxt of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Conduxt 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 |
|---|---|---|---|---|---|---|
| Conduxt this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.9k | Automated safety check: Pass | MIT | |
| Git History Bug Auditben-manes/caffeine | 18k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Qwen Code Memory Leak DebuggerQwenLM/qwen-code | 28k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Code Review Graph Navigatorhandsontable/handsontable | 22k | — | ~939 | Automated safety check: Pass | Custom licence | |
| Andrej Karpathy Skillduolahypercho/andrej-karpathy-skills | 248 | — | ~793 | Automated safety check: Pass | MIT | |
| Verdaccio Change Implementationverdaccio/verdaccio | 18k | — | ~1.3k | Automated safety check: Pass | MIT |
ben-manes/caffeine
Audits a module by walking its git history commit by commit, tracking unresolved issues forward, and reporting the ones that survive to HEAD as findings.
QwenLM/qwen-code
Walks through capturing and comparing V8 heap snapshots to find memory leaks in the Qwen Code Node.js CLI, using tmux and the chrome-devtools CLI.
handsontable/handsontable
Queries a pre-built, Tree-sitter-based code graph of the whole monorepo instead of grepping call chains, for exploring, debugging, refactoring or reviewing code.
duolahypercho/andrej-karpathy-skills
Apply Andrej Karpathy-inspired coding-agent guidelines in Codex.
verdaccio/verdaccio
A workflow for implementing a Verdaccio bug fix, feature or refactor: pick the release lines, check existing options, edit the owning layer, test and add a changeset.
Cranot/roam-code
Codebase comprehension via roam-code CLI. An agent skill from Cranot/roam-code.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Works with
Categories
Orchestrate full-duplex coding agent sessions via ACPX (preferred) or tmux (fallback), composing OpenClaw native tools and community Skills. Conduxt is an agent skill from LeoYeAI/openclaw-master-skills. Orchestrate full-duplex coding agent sessions via ACPX (preferred) or tmux (fallback), composing OpenClaw native tools and community Skills.
Conduxt fits situations like: : implement feature X; refactor the API layer.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill conduxt -a claude-code`. Or copy the skill folder (skills/conduxt in LeoYeAI/openclaw-master-skills) into .claude/skills/conduxt in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill conduxt -a codex`. Or copy the skill folder (skills/conduxt in LeoYeAI/openclaw-master-skills) into .agents/skills/conduxt in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill conduxt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/conduxt, .gemini/skills/conduxt, .github/skills/conduxt and .opencode/skills/conduxt in your project.
Going by SKILL.md and its folder, Conduxt needs a shell for the scripts in its folder and the command-line tools its instructions call (git, gh, npx and gemini). Our summary lists: Node.js; A Bash shell.
SKILL.md contains no URLs. Its commands use git, gh and npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Conduxt is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.9k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Conduxt: Git History Bug Audit (ben-manes/caffeine, 18k stars), Qwen Code Memory Leak Debugger (QwenLM/qwen-code, 28k stars), Code Review Graph Navigator (handsontable/handsontable, 22k stars) and Andrej Karpathy Skill (duolahypercho/andrej-karpathy-skills, 248 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,159 GitHub stars. The repository holds 972 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.