session-finder
Skill0 starsChanged 3 months agoMITView on GitHub
Detects and administers currently RUNNING AI agent sessions on this machine — Claude Code, Codex, OMO/Senpi, gjc, Hermes, OpenCode, aider, Cursor, Gemini CLI — at the process level. Status summary with client grouping and uptime, watch mode, and safe kill (SIGTERM only, validated to refuse non-agent PIDs). Complements session-handoff (which reads completed session logs) — this watches live processes.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- santanusetu/claude-skillstheir own version, first seen Oct 8, 2026
- glebis/claude-skillstheir own version, first seen Jul 1, 2026
- JAVICHILEON/claude---Skillstheir own version, first seen Jul 1, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- glebis/claude-skills★ 410same name
- JAVICHILEON/claude---Skills★ 0same name
- santanusetu/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository69 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- skills/ultimate-browsing/engine/AGENTS.mdAGENTS.md
- 3d-designSkill
- algorithmic-artSkill
- api-testerSkill
- apple-suiteSkill
- appshotSkill
- astra-initSkill
- blindspotSkill
- changelog-genSkill
- claim-auditSkill
- code-reviewSkill
- comment-checkerSkill
- context-budgetSkill
- cron-auditSkill
- css-pro-tipsSkill
- designSkill
- diff-reviewSkill
- doc-readerSkill
- domain-modelingSkill
- env-gateSkill
- ext-scaffoldSkill
- gate-graphSkill
- gh-address-commentsSkill
- gh-fix-ciSkill
- git-masterSkill
- graph-toolsSkill
- grillingSkill
- herdrSkill
- image-genSkill
- json-diffSkill
- linus-levelSkill
- log-analyzerSkill
- log-deviationSkill
- lsp-setupSkill
- merge-quizSkill
- nbj-write-clearlySkill
- net-probeSkill
- open-loopsSkill
- portfolio-auditSkill
- pro-reviewSkill
- proxmox-veSkill
- remove-ai-slopsSkill
- repo-auditSkill
- resume-auditSkill
- sec-headersSkill
- secret-gateSkill
- seo-auditSkill
- session-handoffSkill
- session-rulesSkill
- skill-auditSkill
- skill-creatorSkill
- skill-decaySkill
- skill-optimizerSkill
- skill-pickerSkill
- skill-syncSkill
- social-researchSkill
- subscription-auditSkill
- sys-healthSkill
- The first 60 shown.
The file
Files
Session Finder
Which AI agents are running right now, and what do you do about them.
Commands
python3 scripts/session_finder.py # one-shot scan
python3 scripts/session_finder.py --json # machine-readable
python3 scripts/session_finder.py --watch 10 # re-scan every 10s
python3 scripts/session_finder.py --kill 85819 # SIGTERM (validated)
python3 scripts/session_finder.py --match "my-custom-agent"Detection
Process-level via ps: matches command lines against known agent patterns
(claude, codex, omo/senpi, gajae-code, hermes, opencode, aider, cursor,
gemini). Excludes itself, greps, and the agent-skills test harness. Groups
by client with per-process PID, parent PID, uptime, and command.
Safe kill
--kill PID validates the PID against a fresh detection scan before sending
SIGTERM — it refuses any process that does not match an agent pattern, so
you cannot accidentally kill a system process. SIGTERM only (no SIGKILL);
a hung agent that ignores SIGTERM is your call to handle manually.
Pairs with
session-handoff (read the logs of sessions you found here),
usage-audit (token accounting for those same clients),
session-rules (corrections from those sessions).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.