Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pedroknigge/arkgatenpx agentmods add skills/pedroknigge/arkgate/ark-upgradeWrote 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-upgrade)<a href="https://agentmods.dev/skills/pedroknigge/arkgate/ark-upgrade"><img src="https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-upgrade.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 5.1 | $0.00018 | $0.04978 |
| Opus 5 | $0.00009 | $0.02489 |
| Sonnet 5 | $0.00004 | $0.00996 |
| Haiku 4.5 | $0.00002 | $0.00498 |
Grade B, and why
ark-upgrade scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Stale `~/.claude/skills`, `~/.grok/skills`, or `~/.gemini/config/skills` | Shared homes should be the newest ArkGate on the machine (additive; never downgrade). Refresh: `--install-agent-gates --skills-only --agent-hom How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ark-upgrade — managed ArkGate upgrade
Contener · Guiar · Ordenar. In plain words: contain the write, guide the next step, order leftover mess. This door is Contener: keep the pin current. Skills never enforce — CLI / hooks / CI do.
When: bump the published arkgate package and refresh managed gates.
Not when: session 0 (/ark-adopt) or leftover design (/ark-explore).
When / not when
Use /ark-upgrade when… |
Do not use it when… |
|---|---|
| Bump the pin and refresh managed gates | Session 0 / path missing → /ark-adopt |
Preview then --apply in this turn |
Leftover design / map → /ark-explore; apply Shape → /ark-autopilot |
Steps
- Preview:
arkgate upgrade(no writes). Default is hosts keep — do not retire other hosts’ skills. - Apply in this turn:
arkgate upgrade --apply(installs the bumped package unless--no-install). Needs--plan-digestwhen applying managed files. - Re-run
arkgate-check --doctor. Customized files stay unless you pass--accept-conflicts/--refresh-skills.
Checklist
- Preview unions
--toolswith hosts already in the repo. Multi-agent trees keep every host. - Apply must run the package install of the new pin. Do not skip
npm installunless--no-installis explicit. - Refresh AGENTS.md and CLAUDE.md (same projection schema).
- Prefer project
.agents/skills. Do not duplicate the catalog into~/.codex/skills.
The preview is the source of truth. Do not treat a filename or package version as proof of ownership.
Autonomy contract
Invoking this skill is the approval. Preview, then --apply in this turn.
Stopping at preview is incomplete unless the probe failed or a conflict needs
--accept-conflicts / --refresh-skills consent.
For session 0, start with /ark-adopt (or ark-check --recommend); brownfield
honesty is /ark-adopt before this upgrade flow.
Improvement compass (process preflight)
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 Changed · +11 lines c1c5a0311149
- 4d ago Changed ef455469200e
- 7d ago First seen · 323 lines · 18 tokens per session scan B cf0253076e05
ark-upgrade is a skill published in the GitHub repository pedroknigge/arkgate (1 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 4,978 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
data-mesh-expert
Expert-level data mesh architecture, domain-oriented ownership, data products, federated governance, and self-serve platforms. Use when the user mentions architecture, domain driven, data products, governance, or platform, or when the task involves Data Mesh Principles, Domain-Oriented Data Ownership, Data as a…
code-review-architecture
Architecture-focused code review covering hexagonal boundary violations, DDD anti-patterns, CQRS misuse, and microservices coupling issues. Applied in addition to the language-specific review skill when architecture markers are detected. Invoked when reviewing hexagonal architectures, DDD patterns, or microservices…