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 HelixDevelopment/code --skill multitrackgit clone --depth 1 https://github.com/HelixDevelopment/codeWrote 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/helixdevelopment/code/multitrack)<a href="https://agentmods.dev/skills/helixdevelopment/code/multitrack"><img src="https://agentmods.dev/badge/skills/helixdevelopment/code/multitrack/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/helixdevelopment/code/multitrack"><img src="https://agentmods.dev/badge/skills/helixdevelopment/code/multitrack.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 | $0.00079 | $0.00639 |
| Opus 5.5 | $0.00032 | $0.00256 |
| Sonnet 5.5 | $0.00016 | $0.00128 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
Multitrack 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 2d 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
Multitrack
Automatic multi-track ruler orchestration (§11.4.187): a universal, automatic,
out-of-the-box, inherited-by-reference engine. One conductor session spawns,
drives, resumes, monitors and controls per-track headless workers
(claude -p --output-format stream-json, session id taken from the init
event, success read from result.is_error — never the exit code), with
per-subscription authentication, rate-limit (429) rebind and fallback, and a
crash-resilient self-supervisor over durable state. Bootstrap is idempotent
and auto-invoked on every constitution pull through the §11.4.164 seam.
The consuming project supplies only per-host data:
config/multitrack/<hostname>.yaml. The conductor stays home; tracks execute
in their own checkouts.
Registration
register.sh <project-root> (defaults to $PWD) is the §11.4.164
auto-install trigger — it carries no wiring logic of its own and delegates
entirely to scripts/multitrack/multitrack_bootstrap.sh, whose six
idempotent steps are: install the cwd-hook symlink, check the CLI alias
availability, validate the per-host config (fatal only here — host data is
never invented), seed the orchestrator (reconcile + status), run the
read-only drive-preparation probe, and leave the opt-in supervisor watchdog
off by default.
Activation ceiling and similarity
Active-track count and worker fan-out are bounded by the host's measured budgets (§12.6 / §12.12); a second concurrent heavy build on one host is never scheduled (§11.4.96 UNSAFE catalogue).
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.
- 2d ago Changed · +1 lines · +60 tokens per session e6e126db6ca8
- 1mo ago First seen · 46 lines · 19 tokens per session scan A edadad918e8e
Multitrack is a skill published in the GitHub repository HelixDevelopment/code (2 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 639 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
pipeline-conductor
Operating procedure for the kirocrew-pipeline-conductor agent. Use when a pipeline conductor session is seeded, inspected or debugged. You MANAGE one issue/PR pipeline on one repo: two columns per item (session working? item solved?), send intent, never re-derive a red yourself.
release-notes
Draft a release note section from a commit range, grouped by what the reader gets.
kirocrew-prepare-pr
LOAD THIS FOR EVERY KIRO CREW PR you open or update (Kiro Crew repo only; not other repos or CRs). Runs the whole loop — issue + tier, commit, sync, squash, push, drive CI and AI review to green, fix a red main, arm auto-merge and watch it land (24h). 'push my changes' = prepare-only.
kirocrew-worktree-dev
HARD RULE for developing the Kiro Crew source repo ITSELF (not users' projects): develop, build and verify in a git worktree, never against the live gateway. Covers env setup, main-clone sync, build/dist ordering, flags, previews, cleanup, publish authorization; kirocrew-prepare-pr owns PRs.
vigilante-issue-implementation
Implement a GitHub issue end-to-end when Vigilante dispatches work for a watched repository. Use the provided worktree, respect repository instructions, comment on the issue as work progresses, and report failures back to GitHub.
github-code-review
Review PRs: diffs, inline comments via gh or REST.