sitrep
by IluvatarLabs
One live console to monitor Claude Code and Codex agents across machines, track context and spend, and unblock sessions that need you.
65stars
13forks
TypeScript
Added 11/13/2026
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
Maintainer of this skill?
Installation
# Add to your Claude Code skills
git clone https://github.com/IluvatarLabs/sitrepGetting Started
Guides for using ai agents skills like sitrep.
- Caveman: Cut Claude Token Use by 65%How agent-side prompt compression works, when to use it, and when not to.
- How to Test an AI Skill: A Practical Guide to EvalsEvaluate skills with realistic fixtures, a baseline, and repeatable checks.
- Getting Started with AI SkillsFirst-time install walkthrough for Claude Code, Codex CLI, and ChatGPT.
Compare with similar skills
See how sitrep compares with popular alternatives.
“Who will guard the guards themselves?”
— Juvenal, Satires
You run coding agents on a laptop, a workstation and a server. SITREP shows all of them at once: which are working, which are waiting on you, which are stuck or have failed. Answer the ones that are waiting from the dashboard, without hunting for their terminal.
| The clearest picture of a fleet of agents there is | The fastest way to unblock an agent | The safest dashboard you can point at your sessions |
|---|---|---|
| Every session on every machine as cards, a list or a graph, each with its plan and current step, its agents, model and effort, context fill, git state, cost, and what failed. | Every permission, question and plan that is waiting sits at the top, longest wait first; answer it there or in the terminal, and the first answer wins. | It sends a session only your own answers, messages and commands, never controls a terminal, never starts, stops or restarts a session, stores no transcripts, and runs on a machine you own. |
Try it in two minutes
You need git and Node 24. A simulator stands in for the agents.
git clone https://github.com/IluvatarLabs/sitrep ~/sitrep && cd ~/sitrep
npm ci
npm run dev # the server on :7487, the dashboard on http://localhost:5173
In a second terminal:
cd ~/sitrep
npx tsx scripts/sim.ts --sessions 8 --codex 0.4 --machines 3 --chaos
Install
[!WARNING] SITREP is built for one person on a trusted LAN. It speaks plain HTTP: anyone who can reach port 7487 can read every session, and answering needs a sign-in with the admin secret. Security says how to narrow that.
The server
On a machine that stays on:
git clone https://github.com/IluvatarLabs/sitrep ~/sitrep && cd ~/sitrep
npm ci && npm run build
npx tsx scripts/install.ts --server --bind 0.0.0.0 # dry run: prints every file and command
npx tsx scripts/install.ts --server --bind 0.0.0.0 --apply
It runs as a user service and writes an admin secret to ~/.sitrep/server.env. Open http://<server IP>:7487. Use the
IP address: a host name has to be listed in SITREP_ALLOWED_HOSTS first
(Deploy the server, step 6).
Add a machine
On each machine that runs sessions. Machines → Add a machine in the dashboard gives these commands with your server's address filled in:
git clone https://github.com/IluvatarLabs/sitrep ~/sitrep && cd ~/sitrep && npm ci
npm run build -w codex-reporter # only where Codex runs
npx tsx scripts/install.ts --claude --codex --url http://<server IP>:7487 --token-stdin --apply
Paste the admin secret, then Ctrl-D. Leave out --claude or --codex where that tool is not installed.
Add a machine has the form that pipes the secret from the server.
npx tsx scripts/doctor.ts checks a machine and prints the fix for anything wrong.
npx tsx scripts/uninstall.ts --claude --codex --server lists what it would remove, and --apply removes it
(Uninstall). Your own hooks are never touched.
What it looks like
 |
 |
 |
 |
What it does
- One board for every machine: cards, a list or a graph, grouped by machine or project, filtered by state, machine, project or harness. Tour
- Needs you, and Problems: what is waiting on you, and what is stuck, failed or colliding on a file. What a state means
- Answering: permissions, questions and plans, plus a message,
/compactor/clear. How answering works - Cost and limits: estimated spend by session, model and machine, and each provider's plan window before it runs out. Usage and cost
- History: ended sessions by day, with model, duration, cost and how they ended. Settings and History
- A wall view for a screen left on, and browser notifications when a session needs you, is stuck or fails, or a plan window reaches 90 %. Filter and keys
- Claude Code, Codex and Hermes. Hermes sessions are shown, not answered. A value a harness does not report shows as "—", never as a guess, and every cost is marked "est.". The pieces
What you need
- macOS or Linux, with git. It has not been run on Windows.
- Node 24 on the server; Node 22.15 or later on every other machine (
npm ciwarns there that the repository asks for 24, and installs anyway). - Claude Code 2.1.287 or later.
- Codex 0.162 or later. Answering Codex sessions also needs Codex's managed daemon on that machine.
- Docker, for Hermes: its reporter is a sidecar container.
Docs
- Tour: every view, with screenshots.
- How it works: the pieces, what a session's state means, answering, cost, what is stored.
- Operations: deploying, settings, security, backup, upgrades, troubleshooting.
- Hermes: the sidecar.
License
MIT. Third-party material keeps its own license: THIRD_PARTY_NOTICES.md, and frontend/THIRD_PARTY_NOTICES.md for the logos.
Frequently Asked Questions
What is sitrep?
sitrep is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by IluvatarLabs. One live console to monitor Claude Code and Codex agents across machines, track context and spend, and unblock sessions that need you. It has 65 GitHub stars.
Is sitrep safe to use?
sitrep'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.
How do I install sitrep?
Clone the repository with "git clone https://github.com/IluvatarLabs/sitrep" and add it to your Claude Code skills directory (see the Installation section above).
What programming language is sitrep written in?
sitrep is primarily written in TypeScript. It is open-source under IluvatarLabs on GitHub, so you can review or fork the full source.
Are there alternatives to sitrep?
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 sitrep against similar tools.
Comments (0)
to leave a comment.
No comments yet. Be the first to share your thoughts!
Related Skills
Reverse engineer anything with agents, from app behavior down to native binaries.
453,914
111,553
TypeScript
AI Agentsagent-skillsai
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
301,625
44,496
JavaScript
AI Agentsai-agentsanthropic
Skills for Real Engineers. Straight from my .agents directory.
250,518
21,171
Shell
AI Agents
An agentic skills framework & software development methodology that works.
234,966
20,863
Shell
AI Agentsaibrainstorming