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/action-prefix-systemnpx skills add HelixDevelopment/code --skill action-prefix-systemgit 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 | $0.00025 | $0.00640 |
| Opus 5 | $0.00013 | $0.00320 |
| Sonnet 5 | $0.00005 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
action-prefix-system 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 explaining the action-prefix directive system to a HelixCode user.
The user asked about: {{ARG.action}}
An action prefix turns the first non-blank line of a prompt into a registered instruction. When that line starts with a recognised UPPERCASE token, the token is REPLACED by the action's registered expansion text, the action's rules apply, and the rest of the prompt is executed under that expanded instruction.
Explain the following, and nothing you cannot support:
-
The equivalent invocation forms. All of these resolve to the SAME action, the SAME expansion and the SAME execution:
ACTION_NAME :: restPREFIX::ACTION_NAME :: rest/ACTION_NAME rest/PREFIX::ACTION_NAME restThe reserved default namespace isDEFAULT, and an action resolves with or without that namespace.
-
The grammar rules that decide whether a line is a directive at all:
- it is anchored to the FIRST non-blank line only, so a token appearing mid-prose never matches;
- the action token and namespace are UPPERCASE only (
[A-Z][A-Z0-9_]*); - the namespace separator carries no surrounding spaces
(
PREFIX::ACTION_NAME), which is deliberately distinct from the action-body separator (one space either side of::) so that C++ scope resolution, YAML keys and URLs are never misread as directives; - a leading backslash escapes the prefix so an action name can be discussed literally.
-
Stacked prefixes apply outer-to-inner, left to right.
-
The critical safety rule: a token that matches the grammar shape but is NOT registered must NEVER be silently expanded and never silently dropped. Ask which registered action was meant, or treat the line as ordinary prose. Never invent an expansion for an unknown token.
The registry is data, not code: adding an action is a new registry row. Point
the user at constitution/actions/registry.yaml (overridable with the
HELIX_ACTION_REGISTRY environment variable) as the single source of truth for
which actions exist, and at constitution/skills/action-prefix-system/SKILL.md
for the full specification. Do not guess at the contents of the registry — if
the user needs the current action list, tell them to read that file.
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 · 54 lines · 25 tokens per session scan A 9f1b5fe7b11e
action-prefix-system is a skill published in the GitHub repository HelixDevelopment/code (2 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 640 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…