MoAI-ADK is a Go-based harness that organizes and verifies Claude Code work across planning, implementation, synchronization, and review stages. Developers use it to structure agentic coding tasks, apply quality gates, and route work across language models, while the catalogue entries extend its workflow with skills, hooks, commands, MCP servers, instructions, and settings.
Borrowing it
Nothing to install: this file belongs to modu-ai/moai-adk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/modu-ai/moai-adk/main/.claude/skills/hns-lsel-applier/SKILL.mdgit clone --depth 1 https://github.com/modu-ai/moai-adkWrote 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/modu-ai/moai-adk/hns-lsel-applier)<a href="https://agentmods.dev/skills/modu-ai/moai-adk/hns-lsel-applier"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/hns-lsel-applier/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/modu-ai/moai-adk/hns-lsel-applier"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/hns-lsel-applier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 215 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00181 | $0.03271 |
| Opus 5 | $0.00090 | $0.01636 |
| Sonnet 5 | $0.00036 | $0.00654 |
| Haiku 4.5 | $0.00018 | $0.00327 |
Grade A, and why
hns-lsel-applier 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 12d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hns-lsel-applier — LSEL APPLY engine
Namespace:
hns-lsel-*is user-owned dogfood (CLAUDE.local.md §24). This skill is NOT mirrored intointernal/template/templates/— it lives only in this repo. Graduation tomoai-lsel-*+ 16-language distribution is a separate SPEC (out of scope per spec.md §G).
Token discipline. This body deliberately avoids the literal identifier of the frozen Go applier's write-flag and the literal name of the orchestrator-only user-question channel. Both are referenced by location and role (e.g. "the write-flag at
internal/harness/applier.go:22", "the orchestrator's synchronous user gate") so the REQ-LSEL-003 invariant-grep and the E4 subagent-boundary grep over LSEL surfaces read zero literal matches. The invariants themselves are stated in plain English.
What this skill does
The LSEL loop's PROPOSE→APPLY seam was dead in production: Applier.Apply never ran
(manifest.jsonl absent), CuratorDispatch had 0 production callers, and the frozen
Go applier's write-flag at internal/harness/applier.go:22 (kept false) is the
apply dead-switch (REQ-LSEL-003 — M3 keeps it false by BYPASS, never unfreeze). The
M3 closure routes APPLY through a parallel user-owned applier that writes only to
the six evolvable surfaces (spec.md §B.3), while the frozen Go applier stays
byte-for-byte frozen. Design SSOT:
.moai/reports/moai-local-self-evolution-design-20260804.html §4 ("동결된 Go applier를
우회하는 병렬 사용자 소유 applier를 세운다" — build a parallel user-owned applier that
bypasses the frozen Go one) + §7 (the two-round critique moved the allowlist OUT of
the evolvable skill files into a frozen meta file, and added execution-meta files to
the forced-gate set).
The APPLY engine is the playback hook .moai/hooks/lsel-apply.sh plus this skill's
model-mediated judgment (target validation nuance, approval-marker provenance, blast-
radius reasoning the mechanical hook cannot see). The hook is the load-bearing safety
floor; this skill is the consumer-facing surface that decides WHICH approved decision
to feed it next and how to interpret refusal.
What ships with it
4 files 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.
- 12d ago First seen · 222 lines · 181 tokens per session scan A f286e0d8725d
hns-lsel-applier is a skill published in the GitHub repository modu-ai/moai-adk (1,207 stars, last pushed today), licensed Apache-2.0. It adds 181 tokens to every session and 3,271 once invoked, about $0.0009 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
code-reviewer
Automatic code quality and best practices analysis. Use proactively when files are modified, saved, or committed. Analyzes code style, patterns, potential bugs, and security basics. Triggers on file changes, git diff, code edits, quality mentions.
test-generator
Automatically suggest tests for new functions and components. Use when new code is written, functions added, or user mentions testing. Creates test scaffolding with Jest, Vitest, Pytest patterns. Triggers on new functions, components, test requests, testing mentions.
api-documenter
Auto-generate API documentation from code and comments. Use when API endpoints change, or user mentions API docs. Creates OpenAPI/Swagger specs from code. Triggers on API file changes, documentation requests, endpoint additions.
readme-updater
Keep README files current with project changes. Use when project structure changes, features added, or setup instructions modified. Suggests README updates based on code changes. Triggers on significant project changes, new features, dependency changes.
security-auditor
Continuous security vulnerability scanning for OWASP Top 10, common vulnerabilities, and insecure patterns. Use when reviewing code, before deployments, or on file changes. Scans for SQL injection, XSS, secrets exposure, auth issues. Triggers on file changes, security mentions, deployment prep.
version-check
Recommend which Claude Code version to run, or whether to update. Use when asked which Claude Code version is best/safe, whether to update now, whether a recent release is buggy, or what changed since the installed version.