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 tutur3u/platform --skill tuturuuu-agent-coordinationgit clone --depth 1 https://github.com/tutur3u/platformWrote 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/tutur3u/platform/tuturuuu-agent-coordination)<a href="https://agentmods.dev/skills/tutur3u/platform/tuturuuu-agent-coordination"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-agent-coordination/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/tutur3u/platform/tuturuuu-agent-coordination"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-agent-coordination.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 | $0.00028 | $0.00639 |
| Opus 5.5 | $0.00011 | $0.00256 |
| Sonnet 5.5 | $0.00006 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
tuturuuu-agent-coordination 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 5d 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.
What it actually says
Tuturuuu Agent Coordination
Protect existing work with git status --short, path ownership, and a separate
worktree when needed. Inspect top-level active tmp/agent-coordination/ notes
before overlapping work; missing/noncanonical statuses remain active. Never take
ownership merely because a note is old. Archives are historical context, not locks.
Notes and commit windows are per-checkout. Separate worktrees coordinate through
branches and the remote. Open PR work belongs in .worktrees/ with immediate
bun install. bun setup runs builds; use CI build checks instead.
Read the relevant section of references/coordination-protocol.md for overlap,
handoffs, delegated lanes, generated-output isolation, or cleanup. Create a note
for shared/dirty, overlapping, long-running, or tooling-rule changes. Include Agent,
Intent, Owned paths, Observed dirty paths, Status, Needs, Verification, Risks, and
Commit window. Use statuses working, blocked, handoff, or done; never stage notes.
For multi-lane work spanning PR/CI/delivery wakes, use
references/program-orchestration.md: own the program board and acceptance,
relay complete briefs, drain completed handoffs, and reconcile exact-head proof.
Use its autonomy contract for useful child work during asynchronous waits, inherited briefs and bounded workflow audits. Standing user delegation instructions apply within task authority and actual runtime/resource limits.
Its operating model sets roles, the shared subagent allocation, lead budget grants and receipts; check declared allocations with node scripts/ci/check-agent-budget.js. Apply references/security-default.md to every lane: change-triggered checks, independent review for auth/RLS/CI/token/storage changes, and finding fields.
For assigned ongoing idea/bug/feature intake, read references/request-backlog.md:
capture each outcome before dispatch, recover durable requests on every wake, and
keep implemented work distinct from verified delivery.
Before staging or committing, inspect existing staged paths and claim the window:
bun git-commit-window claim --owner "<agent/task>" --scope "<commit scope>"
Use wait if occupied; release with bun git-commit-window release --token <token>
after completion or abort. Claims last 5–10 minutes. The lock grants no file ownership.
Stage only owned paths. Existing staged work belongs to its owner; do not change it.
For requested integration, retain work until the scoped commit is on main, exact-SHA
main CI passes, bun git-sync completes, and production verification passes.
Clean up only the completed clean worktree and its task branch. Finish the note with
verification and risks; archive your own done note under archive/<YYYY>/ when no
handoff needs visibility. Preserve blocked, unmerged, and other-owned work.
What ships with it
7 files 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.
- 5d ago Changed · +1 lines a4ac4243a03f
- 9d ago Changed e493a1924acb
- 22d ago Changed · +8 lines · +4 tokens per session 2fd0e4dddf19
- 1mo ago Changed 8145874adb0f
- 1mo ago Changed · -172 lines · -67 tokens per session b4aa9880931a
- 1mo ago First seen · 210 lines · 91 tokens per session scan A 61393c3dc402
tuturuuu-agent-coordination is a skill published in the GitHub repository tutur3u/platform (55 stars, last pushed today), licensed Apache-2.0. It adds 28 tokens to every session and 639 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
magic-ui
Use this skill when users want to add, customize, or troubleshoot Magic UI components in React/Next.js projects. It covers component selection, shadcn registry installation (@magicui/), integration patterns, and practical quality checks for accessibility and maintainability.
stacking-prs
Create and manage GitHub native Stacked PRs in this repo with the gh stack CLI. Use when asked to stack PRs, split a large change into a stack, add a layer to a stack, restack or rebase a stack, adopt existing branches or PRs into a stack, check out someone else's stack, or land a stack. Covers creating and submitting…
herdr-kit-workflows
Set up and operate Herdr Kit safely: install and configure the plugin and Mastra Code integration, manage Review and Work repository scope, open primary repository workspaces, synchronize managers, materialize or dematerialize managed worktrees, and update Herdr Kit settings or shortcuts.
herdr-manager-query
Query the authoritative global Herdr Review and Work Manager inventory, recommend actionable PR work, and explicitly materialize confirmed remote-only Review Manager records through the plugin's stable public CLI.
claim-issue
Atomically claim an issue for a developer (human or agent) via the cross-developer lock ref, so two devs never pick up the same task. Syncs with origin first, refuses if already claimed or already done on main, and pushes the claim immediately without touching main or triggering CI.
pi-review-gated-delivery
Use when coordinating review-gated delivery of discrete GitHub issues between one implementation peer and a review-only lead, with user-owned Changesets and approval-gated commits.