Borrowing it
Nothing to install: this file belongs to nubbymong/claude-command-center. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nubbymong/claude-command-center/main/.claude/skills/SessionLoop/SKILL.mdgit clone --depth 1 https://github.com/nubbymong/claude-command-centerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nubbymong/claude-command-center/sessionloop)<a href="https://agentmods.dev/skills/nubbymong/claude-command-center/sessionloop"><img src="https://agentmods.dev/badge/skills/nubbymong/claude-command-center/sessionloop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nubbymong/claude-command-center/sessionloop"><img src="https://agentmods.dev/badge/skills/nubbymong/claude-command-center/sessionloop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00158 | $0.01665 |
| Opus 5.5 | $0.00063 | $0.00666 |
| Sonnet 5.5 | $0.00032 | $0.00333 |
| Haiku 4.5 | $0.00016 | $0.00167 |
Grade A, and why
SessionLoop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the SessionLoop orchestrator. Where StartLoop drives each ticket to
its OWN PR, you take a batch of loop-ready tickets and land them as ONE
human-facing PR: you own a loop/<base>/<slug> integration branch, each ticket is
built in its own worktree and MERGED INTO that branch, and at the end you open a
single squash PR to beta. See ADR-020 (architecture/decisions/…adr-020…) and
docs/loop-autonomy.md.
You never merge the session PR to base. Your merge authority is narrow and
enforced by loop-tree: you may merge a finished ticket branch INTO the loop/*
integration branch (the aggregation step) — loop-tree refuses any non-loop/*
target. A HUMAN merges the session PR to beta, after a desktop test and every gate
(#309 desktop-tested, ci-run matrix, ADR-009 adversarial PASS, owner review). That
boundary is not negotiable; no ticket relaxes it.
PRECONDITION
LoopReady has run and there are loop-ready tickets in scope. If none, say so and
stop — SessionLoop executes a vetted queue, it does not triage. A loop-ready
ticket with no ```loop-record comment is treated as not-ready and skipped. A
filter argument (label, milestone, or ranked slice) scopes the batch; without one,
take all loop-ready tickets on the active release line.
EXECUTE. This is a "don't ask" run.
Once invoked you do not stop to ask per ticket, and one ticket failing does not halt the batch — it is quarantined and you move on. The only things that stop the whole run: an empty queue, losing your GitHub/git identity, or a failure to open/own the integration tree.
Procedure
0. Open the integration tree (once).
Pick a short slug for the batch (e.g. a date or theme: daily-2026-08-25,
ssh-cleanup). Then:
node scripts/loop-tree.mjs open --base beta --slug <slug>
node scripts/session-guard.mjs adopt --path "<the worktree it printed>"
You now OWN the integration worktree on loop/beta/<slug>. This is your home base;
every integrate/submit/close runs from here (they refuse any non-loop/*
branch). Provision its deps if you will build in it (npm ci or a lockfile-matched
junction — never native-rebuild a junction).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 114 lines · 158 tokens per session scan A 29f4330c7021
SessionLoop is a skill published in the GitHub repository nubbymong/claude-command-center (57 stars, last pushed 17d ago), licensed MIT. It adds 158 tokens to every session and 1,665 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.
Other skills, from other repositories
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
team-release
Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.
github-monitor
Watch your GitHub repos across four views - a combined urgency monitor (stale PRs, new issues, releases), a new-issue triage queue, a release upgrade digest, or your own opened-PR tracker.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
start-task
Create a feature branch for a backlog task, switch to it, and start implementation. Use when the user says "start task-123", "work on task-123", "implement task-123", or invokes /start-task with a task ID.