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 pedroknigge/arkgate --skill ark-loopgit clone --depth 1 https://github.com/pedroknigge/arkgateWrote 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/pedroknigge/arkgate/ark-loop)<a href="https://agentmods.dev/skills/pedroknigge/arkgate/ark-loop"><img src="https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-loop/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/pedroknigge/arkgate/ark-loop"><img src="https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-loop.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00022 | $0.00974 |
| Opus 5.5 | $0.00009 | $0.00390 |
| Sonnet 5.5 | $0.00004 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
ark-loop 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 27d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ark-loop — Shortcut to /ark-autopilot
Not a first-class door. One-release redirect. Driving --plan to goal.met is
/ark-autopilot. Do that job now.
Contener · Guiar · Ordenar — this leftover name is not a star.
When / not when
| Use this leftover name when… | Prefer instead |
|---|---|
Plan A has steps; drive to goal.met |
/ark-autopilot |
| Map only | /ark-explore |
| Session 0 | /ark-adopt |
Dual engine (mandatory)
| Engine | Role |
|---|---|
| Deterministic | Only the four mechanical-safe kinds auto-apply; plan tags; gate re-check |
| Exploratory | Read sources; detect concentrated edges / false-green before grinding |
The CLI is a sensor, never the whole job. Claiming done without the exploratory bar for this skill is incomplete.
MCP workspace binding (mandatory)
Before any ark_* MCP tool, call ark_identity with project.expectedRoot set to the exact
workspace root. Continue only when binding.status === "matched" and authoritative === true;
retain projectIdentity.projectId, then pass both expectedRoot and expectedProjectId under
project on every later MCP call. If identity is missing, mismatched, unverified, or the root is
uncertain, do not consume MCP analysis: use the workspace-local CLI and report that MCP
restart/retargeting is required. ark://manifest never satisfies this preflight.
Atomic multi-file work uses ark_prepare_change with the same matched project envelope.
Subagent fan-out (optional, host-dependent)
If the host supports parallel subagents, fan out read-only scouts; otherwise fall back to sequential. Never weaken the gate.
Related onboarding
- Greenfield:
/ark-adoptorark-check --recommend/ark start. - Brownfield:
/ark-adopt.
Mechanical-edit hygiene (outcome gate)
Leftover name, same edit bar as /ark-autopilot if you still land here.
- Header injection must merge into the existing doc comment; the kept result has one
/**, not stacked headers. - Route completion or movement must preserve the original typed
defineRoute<…>(opts, handler)call; reconstruct that call instead of extracting untyped opts/handler constants that drop generics or contextual typing. - A convention-only
*-data.tsstub is not a fix: move the real code or leave the placeholder file uncreated; never writeimport "server-only"; export {}as an empty naming token. - Keep the edit only when the previously clean file stays typecheck-clean. Otherwise roll it back and treat the change as judgment.
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.
- 27d ago Changed · +2 lines 11c2e523e098
- 1mo ago Changed · -6 lines a7a7419df311
- 1mo ago Changed 03baf2c44e64
- 1mo ago First seen · 86 lines · 22 tokens per session scan A c8a0a7589198
ark-loop is a skill published in the GitHub repository pedroknigge/arkgate (1 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 974 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
architecture-patterns
Software architecture patterns and best practices.
architecture-patterns
Software architecture patterns and best practices.
architecture-paradigm-event-driven
Applies event-driven async messaging to decouple producers and consumers. Use when designing real-time or multi-subscriber systems needing loose coupling.
architecture-paradigm-serverless
Applies serverless FaaS patterns for event-driven workloads. Use when designing bursty workloads with minimal infrastructure and pay-per-execution cost model.
extracting-code-structure
Use when listing all methods, functions, or classes in a file, exploring unfamiliar code, getting API overviews, or deciding what to read selectively without loading entire files.
observability
OpenTelemetry, distributed tracing, structured logging, metrics (Prometheus, Grafana, Datadog). Use when implementing monitoring, tracing, or debugging production issues.