Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add skyfox675/agents-skills --skill orchestrating-slotsgit clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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/skyfox675/agents-skills/orchestrating-slots)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/orchestrating-slots"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/orchestrating-slots/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/skyfox675/agents-skills/orchestrating-slots"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/orchestrating-slots.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00179 | $0.06653 |
| Opus 5 | $0.00089 | $0.03327 |
| Sonnet 5 | $0.00036 | $0.01331 |
| Haiku 4.5 | $0.00018 | $0.00665 |
Grade A, and why
orchestrating-slots 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 6d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrating Slots
You are the orchestrator: a long-running coordinator session that dispatches sub-agents into a fixed number of concurrency slots, watches the tracker and CI for events, and keeps the merge pipeline moving. You do not write feature code yourself in this role — you select, lock, dispatch, verify, rescue, and close. This skill covers the loop itself; the protocols it composes live in sibling skills: the issue-locking skill (gh-issue-locking / jira-issue-locking) (claim/release), dispatching-subagents (briefs, model tiers), driving-prs-to-merge (per-PR CI triage and rescue), the issue control-field skill (gh-issue-labels for GitHub labels, jira-issue-fields for Jira fields) (the control taxonomy), and the issue-filing skill (gh-issue-filing for GitHub, jira-issue-filing for Jira) (turning discovered breakage into dispatchable issues).
Project bindings
Define these in the adopting project's CLAUDE.md before running the loop. Refer to them by placeholder everywhere below.
| Binding | Meaning | Example |
|---|---|---|
<integration-branch> |
Branch all PRs target | dev |
<default-branch> |
Repo default branch | main |
<repo-slug> |
Repo slug for gh --repo |
org/repo |
<worktree-dir> |
Where agent worktrees live, branched off fresh origin/<integration-branch> |
.worktrees/<branch> — see the dispatching-subagents skill for the full definition |
<lockfile-install-cmd> |
Lockfile-frozen install | <package-manager> install --frozen-lockfile — see the dispatching-subagents skill |
<pr-ci-workflow> |
PR CI workflow filename (for stale-run checks) | pr-checks.yml |
<required-checks> |
Which check names gate merge (needed to read UNSTABLE) | CI Summary required — see the driving-prs-to-merge skill for the canonical definition |
<bot-reviewer> |
Review bot whose threads may gate merge via required_review_thread_resolution |
a code-review bot |
<claim-label> |
Active-work lock label/field — see the issue-locking skill for semantics | agent-claimed |
<hold-label> |
Operator-hold label/field — see the control-field skill for semantics | do-not-dispatch |
<not-dispatchable-labels> |
Additional labels/fields that exclude an issue from dispatch (project extras beyond blocked and needs-spec-input); case must exactly match what the bootstrap script created |
needs-triage, wontfix (examples — adapt to your label/field set) |
<sentinel-label> |
Label/field marking the pause-sentinel issue | orch:sentinel |
<paused-label> |
Label/field whose presence on the sentinel pauses all dispatch | orch:paused |
<slot-count> and lane caps |
Total concurrency N; leaf/plumbing split | 8 total; 4 leaf + 1 plumbing under cron mode |
| Cadence tunables | Stall window, backup threshold, lock expiry — calibrate to actual CI runtime | 4h stall, >5 PRs + 15 min no-merge backup, 24h lock expiry (assumes 10–15 min CI) |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 265 lines · 179 tokens per session scan A 33ad5a1616ff
orchestrating-slots is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 179 tokens to every session and 6,653 once invoked, about $0.0009 per session on Opus 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.