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 shyftlabs/continuum --skill continuum-streaminggit clone --depth 1 https://github.com/shyftlabs/continuumWrote 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/shyftlabs/continuum/continuum-streaming)<a href="https://agentmods.dev/skills/shyftlabs/continuum/continuum-streaming"><img src="https://agentmods.dev/badge/skills/shyftlabs/continuum/continuum-streaming/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/shyftlabs/continuum/continuum-streaming"><img src="https://agentmods.dev/badge/skills/shyftlabs/continuum/continuum-streaming.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 | $0.00077 | $0.01407 |
| Opus 5.5 | $0.00031 | $0.00563 |
| Sonnet 5.5 | $0.00015 | $0.00281 |
| Haiku 4.5 | $0.00008 | $0.00141 |
Grade A, and why
continuum-streaming 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuum Streaming Skill
Authoritative sources: docs/agent.md §3 and
the EventType enum in continuum/agent/types.py.
Imports
from continuum.agent import AgentRunner
from continuum.agent.types import EventType, AgentEvent
Smallest possible stream
runner = AgentRunner()
async for ev in runner.run_stream(agent, "Tell me a story", user_id="u1", session_id="s1"):
if ev.type == EventType.CONTENT_DELTA:
print(ev.data["content"], end="", flush=True)
run_stream() returns an AsyncIterator[AgentEvent]. Every event
carries: type: EventType, agent_name: str, run_id: str,
data: dict, timestamp, trace_id, span_id.
Full event reference
EventType |
Fires | event.data keys |
|---|---|---|
RUN_START |
Run begins | agent_name, input_preview |
RUN_END |
Run completes | status, latency_ms, usage |
RUN_ERROR |
Run fails | error, error_type |
AGENT_START |
Each agent (incl. handoff target) starts | agent_name |
AGENT_END |
Each agent ends | agent_name, status |
CONTENT_DELTA |
LLM token chunks | content (partial text) |
CONTENT_COMPLETE |
LLM emits a full assistant message | content |
TOOL_CALL_START |
A tool is about to run | tool_name, arguments |
TOOL_CALL_END |
Tool returned successfully | tool_name, result |
TOOL_CALL_ERROR |
Tool raised | tool_name, error |
HANDOFF_START |
Source agent invoking the handoff tool | from_agent, to_agent, reason |
HANDOFF_END |
Target agent finished | from_agent, to_agent |
HANDOFF_RETURN |
Control returned to source (return_to_parent=True) |
from_agent, to_agent |
MEMORY_RETRIEVAL |
Long-term memories injected into prompt | count, query |
MEMORY_STORAGE |
New memories stored after the turn | count |
WORKFLOW_STEP |
Workflow agent advanced | step, agent_name |
LOOP_ITERATION |
LoopAgent completed an iteration | iteration, output |
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.
- 1mo ago First seen · 150 lines · 77 tokens per session scan A 241577bb9e60
continuum-streaming is a skill published in the GitHub repository shyftlabs/continuum (84 stars, last pushed 11d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,407 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 2026-09-03.
Other skills, from other repositories
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
theokit-agents
TheoKit agent/LLM integration — agents/.ts convention (AgentBuilder), the tool() builder, capabilities (advanced/DI), useAgent client hook.
theokit-frontend
TheoKit frontend — file-based routing, layouts, theoFetch typed client, useAgent, React patterns.
theokit-config
TheoKit configuration — the config() builder, plugins, security, storage, agents, build targets.
theokit-database
TheoKit database — Drizzle ORM, SQLite schema, migrations, seeds, db commands.
pulse
Weekly read of what is actually getting built or done, per work-block — from the tracker, the code, and the docs. State of the work, not the stream of events. Distinct from the digest, which is signal since the last run.