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/pedroknigge/arkgate/ark-fixnpx skills add pedroknigge/arkgate --skill ark-fixgit 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-fix)<a href="https://agentmods.dev/skills/pedroknigge/arkgate/ark-fix"><img src="https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-fix.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 | $0.01146 |
| Opus 5 | $0.00009 | $0.00573 |
| Sonnet 5 | $0.00004 | $0.00229 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
ark-fix 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 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.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ark-fix — Shortcut to /ark-autopilot
Not a first-run door. This leftover name is a shortcut. Gate violations are
/ark-autopilot. Do that job now. CLI only validates.
Autonomy contract
Invoking this leftover name is the approval to write the fix. Open importers,
design the port/move, apply, ark-check. Never weaken the config. Never invent
mechanical-safe kinds.
When / not when
| Use this leftover name when… | Prefer instead |
|---|---|
| One change / small cluster just failed the gate | /ark-autopilot |
| Judgment design for a known violation | Session 0 / false-green → /ark-adopt |
Plan B one-pilot checklist (when leftover design, not a single edge)
Empty plan A + leftover design work is not architecture finished. One pilot only.
Write an extraction card (docs/brownfield-adoption.md §6) — never mechanical-safe,
never silent B apply. Kill-switch required. multiPilotBatchForbidden — never
multi-pilot batch.
Dual engine (mandatory)
| Engine | Role |
|---|---|
| Deterministic | CLI / MCP / contract sensors — exit codes, plan kinds, coverage numbers, install status |
| Exploratory | You open this repo's real files and product surface before concluding |
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.
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 729d8248aa08
- 5d ago First seen · 90 lines · 18 tokens per session scan A c7300bfeaba2
ark-fix is a skill published in the GitHub repository pedroknigge/arkgate (1 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 1,146 once invoked, about $0.0001 per session on Opus 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.
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…