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-autopilotgit 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-autopilot)<a href="https://agentmods.dev/skills/pedroknigge/arkgate/ark-autopilot"><img src="https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-autopilot/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-autopilot"><img src="https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-autopilot.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 | $0.00024 | $0.05955 |
| Opus 5.5 | $0.00010 | $0.02382 |
| Sonnet 5.5 | $0.00005 | $0.01191 |
| Haiku 4.5 | $0.00002 | $0.00596 |
Grade A, and why
ark-autopilot 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 9d 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ark-autopilot — Apply the path
Contener · Guiar · Ordenar. In plain words: contain the write, guide the next step, order leftover mess. This door is Guiar: apply leftover design and illegal imports, one small change at a time. Skills never enforce — CLI / hooks / CI do.
When: the user wants architecture cleaned end-to-end, or leftover design after a map.
Not when: map only (/ark-explore), session 0 / config lying (/ark-adopt), or one new file (/ark-place).
Steps
- Read
arkgate-check --doctor(do #1). - Fix import-rule debt; if leftover design remains, apply one small refactor.
When doctor JSON has
noDomainFrontend, that refactor is one pure rule into Domain — not another UI helper. Soft. Silent when Domain already has files. When doctor JSON hasprototypeShortcuts, that refactor is one file-store move into Persistence, or one admin literal behind Domain / an auth tag. Soft. Silent when those houses are absent or the shortcut is already home. - Re-run doctor. Never weaken
ark.config.json.
This is the apply door. Invoking it is the approval. Run arkgate-check --doctor for the next step.
Autonomy contract
The CLI is a sensor and gate. CLI budget: one doctor / --plan; open files; write;
re-check. Forbidden as the result: “4 safe / 4 judgment — approve?”, dumping --plan JSON,
or STOP — invoke /ark-fix / /ark-loop / /ark-contract. Do that work here.
Apply plan A (mechanical-safe and judgment). If leftover design work remains, apply
one small refactor this turn, then re-doctor. Never batch every Shape bet.
Composes explore → sensors → dual plan → write. Validate with ark-check; never weaken the gate.
Team lock: do not edit ark.config.json, arkrules/*, or .ark-baseline.json in this
turn unless the user invoked a steward contract session. Feature diffs use
ark-check --local --base <merge-ref> or ark-check --changed --base <merge-ref>.
--local is the optional cheap path for many worktrees; it cannot combine with
--strict-merge. Growing the baseline is steward-only.
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.
- 9d ago Changed 6d07606f0b6f
- 27d ago Changed · +2 lines 06f2bf982479
- 28d ago Changed · +2 lines 3e565f70ae33
- 1mo ago Changed · +3 lines b630253231a1
- 1mo ago Changed · +2 lines ca52f31ad40f
- 1mo ago Changed · +4 lines d6a8e4a6d91b
- 1mo ago Changed f760ed74d48d
- 1mo ago Changed · +4 lines 3473d4e7b25f
- 1mo ago Changed 507aafd0fb82
- 1mo ago First seen · 298 lines · 24 tokens per session scan A 17502ffa7988
ark-autopilot is a skill published in the GitHub repository pedroknigge/arkgate (1 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 5,955 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.