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-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/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-fix"><img src="https://agentmods.dev/badge/skills/pedroknigge/arkgate/ark-fix.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 | $0.00018 | $0.01316 |
| Opus 5.5 | $0.00007 | $0.00526 |
| Sonnet 5.5 | $0.00004 | $0.00263 |
| Haiku 4.5 | $0.00002 | $0.00132 |
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 23d 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 — 107 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-class door. One-release redirect. Gate violations are
/ark-autopilot. Do that job now. CLI only validates.
Contener · Guiar · Ordenar — this leftover name is not a star.
When / not when
| Use this leftover name when… | Prefer instead |
|---|---|
| One change / small cluster just failed the gate | /ark-autopilot |
| Session 0 / false-green | /ark-adopt |
| One kernel candidate | /ark-runtime |
| One order-plane candidate | /ark-order |
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. Execute that work on /ark-autopilot.
Files nothing imports (one delete at a time)
When doctor.orphanModules lists a file with certainty: no-importer, nothing
imports it and no entry point covers it. Delete one file through the write
gate, run arkgate-check and status again, then the next. A maybe-dynamic or
maybe-unresolved item may still be loaded: open what its evidence names
first. If a framework or loader uses the file, add a glob with a reason to
.ark/entry-points.json instead — never edit ark.config.json for it. No batch
delete, no codemod.
Copies across a wall (one move at a time)
When doctor.crossWallDuplication (status details, --doctor --all) lists a
family, the wall stopped the import and the code was copied. Move one copy to
the family's destination through the write gate (/ark-place names it), point
both sides at it, delete the other copy, run arkgate-check and status again,
then the next family. Never open the wall (allowedCrossSlice, a weaker rule) to
make the copy importable. Copies inside one slice are not listed on purpose. No
batch, no codemod.
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.
- 23d ago Changed · +20 lines 575711123ede
- 27d ago Changed · +2 lines a23a2f27dab6
- 1mo ago Changed · -5 lines 59baa544ac80
- 1mo ago Changed 729d8248aa08
- 1mo 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 today), licensed MIT. It adds 18 tokens to every session and 1,316 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.