Muse Chat Counter Live
See how big a Muse chat is — right in its title, in ~x format
- What
- See how big a Muse chat is — right in its title, in ~x format
- Cost
- Free
- Needs
- Step 0 — before installing anything: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
A Muse skill that stamps a chat's exact per-message token count at the end of its title, so you can see context pressure from the chat list without opening the thread. It refreshes in-turn for free, with a 10-minute wake-on-drift hook as backstop, so it doesn't burn tokens on a standing cron. Built for any Muse user whose long chats need a live gauge before they hit a rotation threshold.
Version:
Install
Copy the install package below, then paste it into Muse📌 Pinned version: commit a9c1b17Step 0 — before installing anything: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Disclosure: this skill runs in every chat (include_in_prompt: true). On every turn in a ticker-enabled chat it reads session_status at the start AND at the end of the turn, writes ~/hooks/state/chat-ticker-<chat_id>.json, and renames the chat when the count moved. It installs one hook per enabled chat, polling every 600 seconds, which only reads that state file and wakes a worker only on drift. It makes no network calls and handles no secrets — but it does rename your chats and install hooks. Prerequisites: a Muse build that exposes session_status with estimated_prompt_tokens, a chat rename tool, and scriptable hooks with a wake mechanism. If any of those is missing, tell me which one and stop — do not install a partial ticker. Install "muse-chat-counter-live" for me. It stamps a chat's live per-message token count at the end of its title in ~x format, refreshed from the exact session_status read, with a 10-minute wake-on-drift loop as backstop. Repository: https://github.com/gordykad/Muse-Chat-Counter_Live (the skill is the skill/ folder plus the templates/ folder at the pinned commit: SKILL.md, skill.yaml, hook-script.sh, worker-prompt.md, state-file.json) Pinned version: install the code at commit a9c1b17e7c49db7c9a07f60253f94f2aaf3eb60a exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/gordykad/Muse-Chat-Counter_Live into a temporary folder, check out commit a9c1b17e7c49db7c9a07f60253f94f2aaf3eb60a, and copy the skill/ and templates/ folders from that checkout. Then compare every file in those folders with the fingerprints recorded for this listing on 2026-10-25: [FINGERPRINTS] - LICENSE: SHA-256 678f99d127476e442026f5a5e36bce856b324f80e4524f709613eff43c20cfca - README.md: SHA-256 348beaf9cefad3ab90980d41adc3052767ab51f059830fd193ed5e72b6e96c5d - examples/README.md: SHA-256 d70b0c4c73d1e1f22e1ae278b8910a7754b6c3d8baa71cd3c291cf6259e180f3 - examples/hook-script.instantiated.sh: SHA-256 779a5ed93d2f1aba16682de7c4e86bef14c5ae9d64537d5c8ca146b86af95c9a - skill/SKILL.md: SHA-256 752fd7738877a2b338a10cde7b384cdfe5e84531581323004475155a61c6ecd2 - skill/skill.yaml: SHA-256 89593c0f328ca29281d14e324567f51119b63c21b67f541a1e497d8ddf8bdc71 - templates/hook-script.sh: SHA-256 c2b5190883b310a2c08d2c8aaa7dd87eef813133d0aea6b027855751857c4d8d - templates/state-file.json: SHA-256 b8341a33caac06eb7b0e8519b7fd6a0d5d9bd81929b45c66614bf2a132ed2628 - templates/worker-prompt.md: SHA-256 1c5a4d131598cf34c073dd5012e80b9f381e9bdcd46379627890716514dfdd24 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read skill/SKILL.md in full, then tell me in plain words: what the skill does when used, whether it connects to a service, whether it reads or sends any personal information or keys, and anything that seems unusual. Confirm from the files: no network calls, no secrets, the hook script reads only the state file, the worker only renames the chat and updates stamped_value. Stop on any red flag and tell me before going further. 3. Only when I say yes, copy skill/ into my skills folder as chat_title_token_ticker/ (SKILL.md + skill.yaml), then enable the ticker on the chat I name, following the 4-step procedure in SKILL.md: write the state file, write the hook script from the template, register the hook with poll_interval_secs 600, dry-run it until the decision is a clean silent, then enable it, rename the chat and verify in the chat list. Never fight a manual rename: if the chat's current name has no ~number suffix and doesn't match the recorded base name, adopt the user's name as the new base name.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
What the scan found — excerpts from the install prompt
- runs commands — script de surveillance bash (modèle) lisant le fichier d'état local avec jq (draft 2026-10-25)
- writes files — écrit ~/hooks/state/chat-ticker-<chat_id>.json et renomme la conversation (draft 2026-10-25)
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.