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/ariaxhan/kernel-claude/app-devnpx skills add ariaxhan/kernel-claude --skill app-devgit clone --depth 1 https://github.com/ariaxhan/kernel-claudeWhat 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 | $0.00049 | $0.00908 |
| Opus 5 | $0.00024 | $0.00454 |
| Sonnet 5 | $0.00010 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
app-dev 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
POLICY: fastlane, never EAS
Local fastlane builds (gym/gradle + deliver/supply) are the default for all native
build + store submission. EAS/cloud builders are a deliberate, stated exception —
never a silent reach (rule: CodingVault/.claude/CLAUDE.md "Mobile builds").
If the project ships its own build CLI (e.g. modelmind's ./mm), extend that — don't
bolt on a second pipeline.
FLOW
- Load source files — Read
fastlane/Fastfile, project build config (build.gradle,*.xcodeproj,app.config.*), any project build CLI, CI config. If no fastlane setup exists,fastlane initand commit the scaffold. (gate: build tooling identified) - Identify environment — dev / staging / production. API endpoints, signing creds,
feature flags are environment-specific. Signing material lives in keychain or
gitignored
_meta/keys/listed in the secrets-backup manifest — never in the tree. (gate: no hardcoded keys or shared signing certs) - Build locally — iOS:
fastlane gym(or project lane). Android:fastlanelane wrappinggradle bundleRelease→ signed AAB. (gate: build completes without error) - JS-only vs native change — JS-only updates may use the project's own OTA mechanism if one exists; any native change requires a full store build. (gate: OTA never used for native changes)
- Run pre-submission checklist (gate: all items pass before submitting):
- Privacy manifests (iOS): all required API reasons declared
- Permissions: only what you use, with clear usage descriptions
- Metadata: screenshots current, descriptions accurate (
fastlane/metadata/) - Version/build numbers: incremented correctly
- Physical device testing: tested on real device (not simulator)
- Deep links: universal links / app links verified
- Push notifications: working in production config
- Crash-free rate: > 99% on staging before promoting
- Bundle size: within limits, no large accidental assets
- Offline behavior: handles no-network gracefully
- iOS submission —
fastlane deliver/pilot: TestFlight (internal → external) → App Store review. (gate: metadata complete; privacy manifests present) - Android submission —
fastlane supplywith a Play service-account JSON: internal → closed/open beta → staged production rollout starting at 5-10%. (gate: data safety form complete; crash rate stable) - Monitor rollout — watch crash rates before expanding staged rollout. Rollback: halt rollout in console; OTA rollback via the project's own mechanism if present. (gate: crash-free rate holds > 99%)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 71 lines · 49 tokens per session scan A 47543409cb38
app-dev is a skill published in the GitHub repository ariaxhan/kernel-claude (12 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 908 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
prolong
Recover and use durable coding-session history from PRO-LONG's local append-only log. Use on long-running coding tasks, after context compaction or session resume, when reconstructing prior decisions or tool results, or before repeating work that may already have been attempted.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
causal-memory
Causal memory for agents — install/setup the causal-memory MCP server, then record decisions/outcomes and recall them before acting. Trigger when the user asks to install or set up causal-memory/agent memory, when causal-memory MCP tools are available and the agent faces a non-trivial decision (architecture, debugging…
a0-create-plugin
Create, extend, or modify Agent Zero plugins. Follows strict full-stack conventions (usr/plugins, plugin.yaml, Store Gating, AgentContext, plugin settings). Use for UI hooks, API handlers, lifecycle extensions, or plugin settings UI.
a0-review-plugin
Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.
create-skill
Wizard for creating new Agent Zero skills. Guides users through creating well-structured SKILL.md files. Use when users want to create custom skills.