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/kirodotdev/kirocrew/self-nudge-loopnpx skills add kirodotdev/KiroCrew --skill self-nudge-loopgit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote 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/kirodotdev/kirocrew/self-nudge-loop)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/self-nudge-loop"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/self-nudge-loop.svg" alt="Measured on agentmods" 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 | $0.00131 | $0.03801 |
| Opus 5 | $0.00066 | $0.01901 |
| Sonnet 5 | $0.00026 | $0.00760 |
| Haiku 4.5 | $0.00013 | $0.00380 |
Grade A, and why
self-nudge-loop scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
TOKEN=$(curl -sf -H "X-Local-Secret: $SECRET" \ How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Nudge Loop
Overview
AutoNudgeService (in kiro_crew.autonudge) keeps a single dashboard chat slot working toward a goal by re-feeding a nudge message every time the slot goes idle. Unlike cron_add, the nudge runs IN the same slot — warm memory, same tools, same conversation history. State persists across gateway restarts via ~/.kiro/crew/autonudge.json.
Usage
Use when the user wants:
- "continuous improvement" that doesn't die between chats
- one long-lived session that auto-resumes whenever idle
- a north-star / roadmap / tasks anchor-file pattern driving autonomous work
- the loop to survive logout and gateway restart
Do NOT use for:
- work best run in fresh isolated session → use plain
cron_add - parallel independent tasks → use
spawn_run - external-system callbacks → use
register_hook
Feature flag
On by default. To disable:
export KIROCREW_AUTONUDGE=0 # add to systemd unit Environment= or ~/.kiro/crew/env
kirocrew restart
When disabled, the REST API returns 503 and the UI popover surfaces the error.
Core Concepts
Reactive idle timer — after every HOOK_EVENT_STOP (turn completes), the service arms a per-slot asyncio timer for idle_secs. If a user message arrives, timer cancels (user wins). If the timer fires, the configured nudge is injected into the slot as a distinctively-styled msg msg-nudge bubble and _run_chat processes it normally.
Three files the agent owns (convention, not enforced):
| File | Role |
|---|---|
north_star.md |
Immutable goal. Why the loop exists. |
roadmap.md |
Phases / milestones. Agent may edit as it learns. |
tasks.md |
Active checklist. Agent checks off / adds items each cycle. |
Kill switches (any of the below):
- The looping agent itself calls the
autonudge_stopMCP tool — preferred, works from inside the loop with no ID lookup needed. The tool identifies the current slot fromKIROCREW_SESSION_KEYand deletes the bound loop. - Click the Stop loop button in the UI popover.
- Create the configured
STOPsentinel file — next cycle halts. max_cyclesreached — loop deactivates (not removed, so you can resume).DELETE /api/autonudge/{loop_id}orautonudge_svc.remove(id).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 241 lines · 131 tokens per session scan A bd54f53a075c
self-nudge-loop is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed yesterday), licensed Apache-2.0. It adds 131 tokens to every session and 3,801 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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-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.
copilotkit-integrations
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
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…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.