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/workable-item-lifecyclenpx skills add HelixDevelopment/code --skill workable-item-lifecyclegit 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 | $0.00027 | $0.00678 |
| Opus 5 | $0.00014 | $0.00339 |
| Sonnet 5 | $0.00005 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
workable-item-lifecycle 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 guiding a HelixCode user through a workable item's lifecycle.
The workable-items database is the single source of truth. The Issues, Fixed and summary documents — and their exported siblings — are GENERATED from it. Never hand-edit a generated document: the next regeneration silently reverts the edit and the tracker starts lying.
STATUS — the closed set:
Queued, In progress, Ready for testing, In testing, Reopened,
Operator-blocked, the type-appropriate terminal closure, and Obsolete.
TYPE-AWARE CLOSURE — the terminal status depends on the type, and mismatching them is an error:
Bugcloses as FixedFeaturecloses as ImplementedTaskcloses as Completed
Apply these rules:
-
CLOSING REQUIRES CAPTURED EVIDENCE. An item closes on proof that the change works for the end user — a real run, with its output. Compiling, a green grep, a configuration change, or the absence of an error are not evidence. The strongest form is a check that would FAIL if the defect returned.
-
CLOSING A DEFECT REGISTERS A PERMANENT GUARD. In the same change as the fix, add a regression check that reproduces the original defect and then flips to a standing guard. A closure with no falsifiable guard invites silent recurrence.
-
REOPENING MUST RECORD ITS SOURCE. Who observed it, on what date, why (the reason), and the evidence that justifies the reopen. A reopen without evidence is not a reopen, it is a guess.
-
A RECURRENCE REOPENS THE ORIGINAL ITEM. Never mint a fresh id for a defect that returned — that hides the fact that a previous fix did not hold.
-
Operator-blockedMUST ENUMERATE WHAT WOULD UNBLOCK IT. List the specific decisions or actions that would clear the block. A blocked item with no options is a dead end. -
ObsoleteMUST SAY WHY — superseded by a design change or a later decision, the feature was removed, a duplicate, or an unsupported configuration — and name the item that supersedes it, where there is one.
Tell the user the exact status and type their situation calls for, and what
evidence it needs. The full lifecycle contract is documented in
constitution/skills/workable-item-lifecycle/SKILL.md.
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 · 57 lines · 27 tokens per session scan A a7e701b4f34e
workable-item-lifecycle is a skill published in the GitHub repository HelixDevelopment/code (2 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 678 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…