by 100yenadmin
Index, search, summarize, and approval-gate local Codex sessions through OpenClaw/MCP. Agent-first recall and dry-run orchestration for Codex-heavy work.
# Add to your Claude Code skills
git clone https://github.com/100yenadmin/Lossless-Codex-Orchestrator-LCOGuides for using ai agents skills like Lossless-Codex-Orchestrator-LCO.
Lossless-Codex-Orchestrator-LCO is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by 100yenadmin. Index, search, summarize, and approval-gate local Codex sessions through OpenClaw/MCP. Agent-first recall and dry-run orchestration for Codex-heavy work. It has 69 GitHub stars.
Lossless-Codex-Orchestrator-LCO's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/100yenadmin/Lossless-Codex-Orchestrator-LCO" and add it to your Claude Code skills directory (see the Installation section above).
Lossless-Codex-Orchestrator-LCO is primarily written in TypeScript. It is open-source under 100yenadmin on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Lossless-Codex-Orchestrator-LCO against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
LCO turns local Codex sessions into searchable, bounded, approval-aware work objects for OpenClaw.

Use it when an agent or user needs to answer: what sessions are active, what did they plan, what did they finish, what files did they touch, and what is the next safe action without rereading raw transcripts.
| What LCO gives agents | Why it matters |
|---|---|
| Searchable local session memory | Find plans, finals, touched files, and refs without raw transcript rereads. |
| Bounded evidence expansion | Read compact public-safe briefs before opening larger source material. |
| Approval-gated boundaries | Dry-run Codex actions and verify matching audit ids before any live control. |
| OpenClaw/MCP tools | Use the same local-first recall and approval-bounded surfaces from agent workflows. |
Setup · Contributing · Agent Instructions · Agent Skill · OpenClaw Plugin · Security · Code of Conduct · Vision · Privacy · Claude Boundary · Claim Audit · Release Notes · 1.2.0 Notes · 1.1.4 Notes · 1.0 Notes · License
Codex is powerful, but long-running local work can become hard to supervise once you have dozens or hundreds of threads. LCO gives your orchestrator agent a safe operating picture: search first, inspect compact session cards, expand only bounded evidence, and dry-run the next action before anything live happens.
If you are here to contribute, start with CONTRIBUTING.md. If you are an agent working in this repository, read AGENTS.md before editing files.
LCO is a local-first orchestration layer for Codex-heavy work:
loo_* tools through MCP and the OpenClaw pluginexecute:false
tool calls so an agent can probe before dry-run handoff without mutationThe result is a staged recall loop:
Requirements:
~/.codex/sessionsloo_* tools through OpenClawStable install:
npm install -g lossless-openclaw-orchestrator@latest
loo doctor
Beta train, when you explicitly want the newest prerelease:
npm install -g lossless-openclaw-orchestrator@beta
Package channels:
latest is the stable public channel.beta is the active prerelease train.next is reserved for release candidates.Full first-run instructions live in docs/SETUP.md.
Choose where LCO stores its local index. The default is already under
~/.openclaw, but setting it explicitly makes setup easier to inspect:
export LOO_DB_PATH="$HOME/.openclaw/lossless-openclaw-orchestrator/orchestrator.sqlite"
Index local Codex sessions:
loo index codex --max-files 500 "$HOME/.codex/sessions" "$HOME/.codex/archived_sessions"
Optional: allow read-only recall from one or more OpenClaw LCM peer databases:
export LOO_LCM_DB_PATHS="$HOME/.openclaw/lcm.db"
Check local readiness:
loo doctor
loo onboard status --strict
If agents will author PRs, issue comments, or closeouts in the repo, also copy
the provenance snippets from docs/SETUP.md
into the repo's AGENTS.md and CLAUDE.md files.
Search for a session:
loo search "billing bridge proposed plan"
Describe a result:
loo describe codex_thread:<thread-id>
Expand a bounded brief:
loo expand-ref --profile brief --token-budget 1000 codex_thread:<thread-id>
Expand from a query when you do not know the ref yet:
loo expand-query --profile brief --token-budget 1000 "billing bridge"
For normal agent workflows, start with the compact public/operator facade
instead of treating every loo_* tool as a peer:
| Step | Tool | Purpose |
|---|---|---|
| 1 | loo_prepared_inbox |
Start from the compact prepared-state operating picture. |
| 2 | loo_describe_ref |
Look up a specific session or source ref from the inbox. |
| 3 | loo_expand_query |
Expand one bounded evidence brief when the ref is not known. |
| 4 | loo_recent_sessions |
Refresh recent or active cards after reads or approved actions. |
| 5 | loo_attention_inbox |
Review the compact attention queue before choosing a next action. |
| 6 | loo_project_digest |
Produce a bounded provenance and handoff digest. |
| 7 | loo_codex_control_dry_run |
Create the exact dry-run action packet and approval hashes. |
| 8 | loo_codex_resume_thread |
Run an approved resume only after the matching audit id. |
Other declared tools remain available as workflow_detail, proof_debug, or
internal_low_level surfaces for setup, diagnosis, proof, and recovery. Their
existence is deliberate: normal agents should start from the facade, then drop
to the lower tiers only when the compact path returns a specific next step or
blocker.
loo_codex_control_dry_run returns the audit id and hashes an agent should show
before any live start/resume/send/steer/interrupt call. Live control requires
the matching approval_audit_id.
Live Codex control results include proof_state fields for
accepted_by_transport, started, completed, persisted, and
unverified_pending. Transport acceptance is not durable execution: when
unverified_pending is true, run the returned next_proof read-only tool call
before claiming the turn or thread completed, persisted, or is safe to build on.
The packaged agent playbook is skills/lossless-openclaw-orchestrator/SKILL.md.
Naming policy: LCO is the public product abbreviation and lco_* is the
forward public alias target for new user-facing tool names. The currently
callable OpenClaw/MCP tools still use the historical loo_* runtime prefix, so
examples that must run today continue to show loo_* until #434 lands a tested
alias layer. Do not delete or silently rename the loo_* tools; keep them as
backward-compatible aliases when lco_* aliases are added.
Run the MCP server directly:
loo-mcp-server
Typical MCP client entry:
{
"mcpServers": {
"lossless-openclaw-orchestrator": {
"command": "loo-mcp-server"
}
}
}
Install the OpenClaw plugin from npm:
openclaw plugins install lossless-openclaw-orchestrator@latest
openclaw plugins list --json
Verify the package and OpenClaw gateway path:
loo openclaw dogfood --profile lco-dogfood --install-source lossless-openclaw-orchestrator@latest --required-tool loo_doctor --required-tool loo_search_sessions --strict
loo openclaw tool-smoke --profile lco-dogfood --required-tool loo_doctor --required-tool loo_search_sessions --strict
OpenClaw gateway setup may require local credential, device-pairing, token, or scope approval steps before tool smoke can pass. LCO reports those as setup blockers, not package failures. See docs/SETUP.md and docs/OPENCLAW_PLUGIN.md.
LCO is Codex-first and local-first.
Default behavior: