Contextual Commit Messages
yamadashy/repomix
Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.
Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure…
$ npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install modu-ai/moai-adk hns-lsel-applier --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/modu-ai/moai-adk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/hns-lsel-applier .claude/skills/hns-lsel-applier && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "hns-lsel-applier" agent skill from https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-lsel-applier into .claude/skills/hns-lsel-applier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hns-lsel-applier", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-lsel-applierType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install modu-ai/moai-adk hns-lsel-applier --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/modu-ai/moai-adk.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/hns-lsel-applier .agents/skills/hns-lsel-applier && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hns-lsel-applier" agent skill from https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-lsel-applier into .agents/skills/hns-lsel-applier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hns-lsel-applier", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install modu-ai/moai-adk hns-lsel-applier --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/modu-ai/moai-adk.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/hns-lsel-applier .cursor/skills/hns-lsel-applier && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hns-lsel-applier" agent skill from https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-lsel-applier into .cursor/skills/hns-lsel-applier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hns-lsel-applier", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/modu-ai/moai-adk.git --path .claude/skills/hns-lsel-applier--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install modu-ai/moai-adk hns-lsel-applier --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/modu-ai/moai-adk.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/hns-lsel-applier .gemini/skills/hns-lsel-applier && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "hns-lsel-applier" agent skill from https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-lsel-applier into .gemini/skills/hns-lsel-applier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hns-lsel-applier", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install modu-ai/moai-adk hns-lsel-applierInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/modu-ai/moai-adk.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/hns-lsel-applier .github/skills/hns-lsel-applier && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "hns-lsel-applier" agent skill from https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-lsel-applier into .github/skills/hns-lsel-applier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hns-lsel-applier", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install modu-ai/moai-adk hns-lsel-applier --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/modu-ai/moai-adk.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/hns-lsel-applier .opencode/skills/hns-lsel-applier && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hns-lsel-applier" agent skill from https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-lsel-applier into .opencode/skills/hns-lsel-applier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hns-lsel-applier", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
hns-lsel-applierLocal Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure…
Hns Lsel Applier is an agent skill from modu-ai/moai-adk. Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001 M3). Reads an approved decision.json, validates the target against the frozen allowlist (.claude/lsel/frozen-allowlist.json), mechanically refuses execution-meta targets lacking a synchronous-approval marker, applies the referenced diff.patch, appends an apply-ledger.jsonl row, and commits one…
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `apply_test.sh`, `rollback_rehearsal_test.sh` and `verify.sh`).
It sits in Development, covering Commit messages. The repository describes itself as: Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16… The licence is Apache-2.0.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 2aab5f7. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepGlobBashFrom allowed-tools in the SKILL.md frontmatter.
Ships script files (Shell), which the agent can run.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Hns Lsel Applier loads about 3k tokens when it runs. Until then it costs about 189 tokens; SKILL.md has 1,228 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Grep, Glob, BashAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from modu-ai/moai-adk at commit 2aab5f7, republished under its Apache-2.0 licence (© modu-ai). 1,228 words, ~3,022 tokens.
.claude/skills/hns-lsel-applier/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.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.
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.
lsel-apply.sh <decision.json> performs five steps. Steps 1-2 are the safety floor;
steps 3-5 are the playback.
decision.json is matched against the frozen_patterns regex list in
.claude/lsel/frozen-allowlist.json. A match → REFUSE: a row is appended to
.moai/logs/lsel-reject.log naming the rejected path and category frozen-path,
NO file is written, and the hook exits 2.execution_meta categories —
(i) the frozen allowlist meta file itself, (ii) an applier/curator skill body
(hns-lsel-applier/, hns-lsel-curator/), (iii) the apply hook
(.moai/hooks/lsel-*.sh), (iv) the settings.local.json hook-registration
subblock — the hook checks decision.json for a synchronous-approval marker (a
synchronous_approval object with decision: "approved", produced by the
orchestrator's synchronous user gate). No marker → REFUSE: reject-log row with
category execution-meta, exit 3, no write. With marker → proceeds (the refusal
is keyed on the absent marker, NOT on the category match alone). The refusal
semantics mirror the M2 csa_refusal_test.sh fixture exactly.git apply (playback of an already-approved decision).
Only the paths declared in the patch are staged — never git add -A (working-tree
hygiene)..moai/state/lsel/apply-ledger.jsonl:
{proposal_id, target_surface, ts, result:"applied", commit_sha, category}. This
is the manifest the frozen Go applier never produced, finally real in user-owned
space.feat(lsel-<proposal-id>): ... Conventional
Commit on the current (feature) branch (REQ-LSEL-004). The ledger row's
commit_sha is backfilled from the commit's short SHA.A no-arg invocation is a clean no-op (exit 0) so an empty approved-queue does not derail a loop pass.
When this skill is invoked to drive an APPLY pass, your job on top of the mechanical hook is:
proposal.md + self-critique.md at
.moai/state/lsel/proposals/<id>/. A proposal with status: blocked (any
UNRESOLVED self-critique objection) MUST NOT be fed to the hook — return a blocker
report instead.synchronous_approval object must
carry a real orchestrator-produced approval artifact (the synchronous user-question
channel the orchestrator owns per askuser-protocol.md). A marker the loop fabricated for
itself is the self-amending-handcuffs failure mode (REQ-LSEL-002); the hook's
mechanical check is the floor, your provenance judgment is the ceiling. This skill
is a subagent mechanism and NEVER invokes the orchestrator-only user-question
channel; return a blocker report and let the orchestrator run the gate.internal/harness/applier.go:22 — it MUST stay false. If M3's bypass ever drifts
toward unfreezing the Go applier, return a blocker (AP-LSEL-002).internal/harness/applier.go:22 stays false (REQ-LSEL-003). The bypass is
parallel and user-owned; the frozen applier is reference-only.internal/template/templates/**,
.claude/rules/moai/**, AGENTS.md, retained agents, moai-* skills, the frozen
Go applier / curator_dispatch.go, and .moai/config/sections/** are
byte-for-byte untouched. The allowlist hard-rejects them (step 1).lsel-apply.sh
(REQ-LSEL-008). The hook only consumes already-approved decisions; it does not
author proposals or bless them. The M4 verify.sh runs only AFTER an apply has
committed — it does not create a new apply; it never self-approves.After an apply commits a proposal, VERIFY proves the apply was safe. VERIFY has two layers — both MANDATORY:
verify.sh (bash-testable)verify.sh --proposal-dir <p> --repo-root <r> [--timeout SECS] [--feedback-file <f>]
runs the proposal's frontmatter verify_command with a timeout-retry-once
policy and auto-reverts on a second failure:
verified:true, stop. On
TIMEOUT-class failure → attempt 2 (flaky tolerance — report §10 P3: "retry
once on timeout so a correct proposal isn't flipped by noise"). On
NON-TIMEOUT-FAIL → attempt 2 (allows the "second non-timeout failure" of
AC-LSEL-015 clause 3 to materialize before revert fires).verified:true. Any failure (timeout OR non-timeout) →
verified:false + auto git revert lsel-<proposal-id> + the proposal's
feedback_*.md is marked verified: false.{"stage":"verify","verified":true|false,...} row — the load-bearing signal./moai gate superset (model-mediated)/moai gate (lint+format+type+test) is MANDATORY after every apply — it is
NOT optional. A bash hook cannot invoke a Claude Code slash command directly,
so the gate runs MODEL-SIDE: when this skill drives an APPLY pass, the
orchestrator/model runs /moai gate after the mechanical apply + verify. The
proposer-authored verify_command alone is circular (report §11 mustFix
B#6 / AP-LSEL-004): a proposer can author a verify_command that its own change
satisfies. /moai gate is the independent check — lint, format, type-check,
and the test suite exercise surfaces the proposal never touched. Treat a
mechanical verify_command PASS without a green /moai gate as an unverified
apply.
lsel-apply.sh commits and verify.sh reports, run /moai gate
(the MANDATORY superset). If the gate fails, the apply is unverified even if
verify.sh reported verified:true — treat it as a VERIFY failure and revert.verify.sh or gate-driven) MUST be surfaced
to the orchestrator as a blocker report — the orchestrator, not this skill,
confirms a revert with the user. Never run /moai gate's user-facing surface
from inside this subagent mechanism; return a blocker report.# M4 VERIFY characterization test (AC-LSEL-015) — hermetic temp repo:
.claude/skills/hns-lsel-applier/verify_test.sh
# the verify ledger row carries the outcome:
grep '"stage":"verify"' .moai/state/lsel/apply-ledger.jsonl# 1. APPLY characterization test (AC-001/002/005/008/013) — hermetic temp repo:
.claude/skills/hns-lsel-applier/apply_test.sh
# 2. Rollback-rehearsal SHIP GATE (AC-014):
.claude/skills/hns-lsel-applier/rollback_rehearsal_test.sh
# 3. REQ-LSEL-003 frozen-flag re-verify (post-apply). The frozen Go applier's
# write-flag at internal/harness/applier.go:22 MUST read `false`, and no LSEL
# surface (skills/hooks/state/allowlist) references that identifier as mutable.
# (The literal identifier is intentionally not written here; find it at line 22
# of the frozen file and grep LSEL surfaces for it — expect zero hits.)
sed -n '22p' internal/harness/applier.go # MUST show the `= false` write-flag line
# 4. The apply ledger carries the new row:
tail -1 .moai/state/lsel/apply-ledger.jsonl.moai/specs/SPEC-LSEL-LOCAL-EVOLUTION-001/{spec,plan,acceptance,progress}.md.moai/reports/moai-local-self-evolution-design-20260804.html
§4 (user-owned parallel applier), §7 (allowlist relocation + execution-meta forced
gate), §10 P3, §11 mustFix A#1/A#5/A#8.internal/harness/applier.go:22 (the frozen
write-flag), internal/harness/curator_dispatch.go..claude/skills/hns-lsel-curator/SKILL.md
(CSA forced-gate doctrine + the Tier-4 DEAD finding)..claude/skills/hns-lsel-curator/csa_refusal_test.sh
(the refusal rule this hook enforces mechanically).internal/template/split_namespace_test.go,
internal/template/internal_content_leak_test.go (must NOT flag a hns-lsel-applier
leak — this skill is dogfood, never templated).© modu-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files in .claude/skills/hns-lsel-applier of modu-ai/moai-adk.
Open the folder on GitHubat commit 2aab5f7
Hns Lsel Applier next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hns Lsel Applier this skillmodu-ai/moai-adk | 1.2k | — | ~3k | Automated safety check: Notes | Apache-2.0 | |
| Contextual Commit Messagesyamadashy/repomix | 29k | 1 repos | ~2.7k | Automated safety check: Pass | MIT | |
| React Router Release Notes Prepremix-run/react-router | 57k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Caveman Commitvishiri/fantasia-archive | 409 | 13 repos | ~642 | Automated safety check: Pass | GPL-3.0 | |
| PR Finalize Reviewmicrosoft/garnet | 12k | — | ~3.1k | Automated safety check: Pass | MIT | |
| ToolJet Multi-Repo CommitToolJet/ToolJet | 41k | — | ~1.3k | Automated safety check: Pass | AGPL-3.0 |
yamadashy/repomix
Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.
remix-run/react-router
Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.
vishiri/fantasia-archive
Ultra-compressed commit message generator. An agent skill from vishiri/fantasia-archive.
microsoft/garnet
Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.
ToolJet/ToolJet
Commits changes across ToolJet's root repo and its server/ee and frontend/ee submodules, writing messages from the diffs and updating submodule pointers in order.
addyosmani/agent-skills
Sets git habits for every change: short-lived branches, atomic commits with descriptive messages, clean pull requests, plus versioning, tagging and changelogs for releases.
modu-ai/moai-adk
Builds hand-editable SVG diagrams from computed layout coordinates, lints the source and renders a 2x PNG, with rules for when mermaid is the better choice.
modu-ai/moai-adk
Reference for MoAI-ADK's core development principles: TRUST 5 quality gates, SPEC-first domain-driven workflow, agent delegation and token budgeting.
modu-ai/moai-adk
Manages SPEC documents for MoAI-ADK development, with GEARS or EARS requirement notation, acceptance criteria and a link into the Plan-Run-Sync workflow.
modu-ai/moai-adk
Drives test-first development through the RED, GREEN, REFACTOR cycle, with a config switch that selects between TDD and a DDD workflow for existing code.
modu-ai/moai-adk
Gives each SPEC its own Git worktree with a registry of active workspaces, base-branch sync and cleanup of merged ones, inside the MoAI-ADK workflow.
modu-ai/moai-adk
Watches a pull request's CI checks after creation, separates required from auxiliary failures, applies limited safe fixes and escalates anything semantic to you.
Categories
Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure…. Hns Lsel Applier is an agent skill from modu-ai/moai-adk.sh for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001 M3).
Hns Lsel Applier fits situations like: tasks that involve Commit messages.
Run `npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a claude-code`. Or copy the skill folder (.claude/skills/hns-lsel-applier in modu-ai/moai-adk) into .claude/skills/hns-lsel-applier in your project. Claude Code loads it when a task matches its description.
Run `npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a codex`. Or copy the skill folder (.claude/skills/hns-lsel-applier in modu-ai/moai-adk) into .agents/skills/hns-lsel-applier in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add modu-ai/moai-adk --skill hns-lsel-applier -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hns-lsel-applier, .gemini/skills/hns-lsel-applier, .github/skills/hns-lsel-applier and .opencode/skills/hns-lsel-applier in your project.
Going by SKILL.md and its folder, Hns Lsel Applier needs a shell for the scripts in its folder and the command-line tools its instructions call (git). Our summary lists: A Bash shell. Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Hns Lsel Applier is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Hns Lsel Applier: Contextual Commit Messages (yamadashy/repomix, 29k stars), React Router Release Notes Prep (remix-run/react-router, 57k stars), Caveman Commit (vishiri/fantasia-archive, 409 stars) and PR Finalize Review (microsoft/garnet, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
modu-ai (a GitHub organization) maintains it in modu-ai/moai-adk, which has 1,230 GitHub stars. The repository holds 48 skills in this directory. The repository was last updated on October 9, 2026.
Source: modu-ai/moai-adk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.