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 agentmods add skills/helixdevelopment/code/multitracknpx skills add HelixDevelopment/code --skill multitrackgit clone --depth 1 https://github.com/HelixDevelopment/codeWhat 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 | $0.00019 | $0.00577 |
| Opus 5 | $0.00010 | $0.00289 |
| Sonnet 5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00058 |
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 yesterday.
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
You are helping a HelixCode user run parallel multitrack work streams.
Multitrack development runs several isolated checkouts at once, each on its own branch, so independent work proceeds in parallel without the streams colliding. Apply these invariants:
-
ISOLATION BY CONSTRUCTION. Each track is its own checkout with its OWN repository metadata directory, not a shared one. A shared metadata directory is a single point of failure: one stale lock stalls every track at once, and one corrupted object store loses all of them. Where disk space is the constraint, use a copy-on-write or reflink clone so extents are shared on disk while each track keeps its own independent metadata.
-
ONE FEATURE, ONE BRANCH NAME. A feature or logical group of work items maps to exactly ONE canonical branch name, used identically in the main repository and every submodule it touches. Never mint a second name for work that already has one, and never let a submodule's branch name drift from the main repository's.
-
TRACK-QUALIFIED IDENTITY. Never identify a track by the bare directory basename. Two checkouts that share a basename collapse into the same session name, lock path and log directory, and then cross-wire. Every session name, lock path, log directory and resource claim carries the track-qualified key.
-
EXCLUSIVE RESOURCES HAVE ONE OWNER. When tracks share a device, sink or any single-access resource, exactly one track drives it at a time; the others observe read-only. Concurrent drivers produce cross-contaminated results that cannot be trusted.
-
MERGE THE TRUNK IN OFTEN. Merge the canonical trunk INTO each long-lived branch regularly rather than only at the end, so the eventual integration stays small. Merge, never rebase, so no commit is lost.
Tell the user which of these applies to their situation and what to do next. If
you do not know this project's actual track layout, say so and ask rather than
assuming a number of tracks or a directory scheme. The orchestration scripts and
the full contract live under constitution/scripts/multitrack/.
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.
- yesterday 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 4d ago), licensed MIT. It adds 19 tokens to every session and 577 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
copilotkit-setup
Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
runtime
@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…