Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Public Plugin Packaging · agentlas-ai | DecimalAI

agent toolingby agentlas-ai

Public Plugin Packaging

agentlas-ai/public-plugin-packaging

Source agentlas-ai/agentlas-os ↗License Apache-2.0

Use when packaging this meta-agent for public Codex plugin registration, Claude Code installation, GitHub release, one-line terminal install, or open-source distribution.

SkillScore95Maintained

Automatic

AI Engineer pack

Last verified 8/17/2026

What it changes

Passed 21 of 22 test cases with the skill, and 8 of 22 without it.

Without skill36%

With skill95%

Checks it passed that the model alone missed

Specifies .claude/commands/meta-agent.md as the location
Specifies codex/marketplace.json as the required file path
Specifies scripts/install.sh as the installer script location

and 13 more in the full report

13 fixed8 passed either way1 still failing0 broke

Pass-rate lift: +59 pp
Tokens: -26%
Agent turns: 0%
Response time: -44%

Model gemini-3.6-flashMeasured 8/17/2026v321 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/agentlas-ai-public-plugin-packaging/SKILL.md https://app.decimal.ai/s/agentlas-ai-public-plugin-packaging/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add agentlas-ai-public-plugin-packaging, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/agentlas-ai-public-plugin-packaging/ and pins it in .decimal/skills.lock

decimalai skills add agentlas-ai-public-plugin-packaging

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/agentlas-ai-public-plugin-packaging/SKILL.md https://app.decimal.ai/s/agentlas-ai-public-plugin-packaging/SKILL.md

Raw file: /s/agentlas-ai-public-plugin-packaging/SKILL.md ↗ · machine-readable summary at /s/agentlas-ai-public-plugin-packaging.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

Where must the plugin manifest file be located for a Codex plugin package structure?

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies .codex-plugin/plugin.json as the plugin manifest location	Missed	Passed

case-08 · gemini-3.6-flash · 8/17/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md23 linessingle file

Public Plugin Packaging

Checklist

codex/marketplace.json exists.
Codex plugin has .codex-plugin/plugin.json.
Codex plugin includes at least one SKILL.md.
Codex plugin includes commands/<slug>.md for the package command.
.claude/commands/meta-agent.md exists.
.claude/commands/<slug>.md exists for the package command.
.claude/agents/agentlas-core-engine-meta-agent.md exists.
.claude/skills/agentlas-core-engine-meta-agent/SKILL.md exists.
.gemini/commands/<slug>.toml exists for Gemini CLI custom commands.
.agentlas/global-commands.json exists and final handoff includes global_commands.
scripts/install.sh supports one-line installation.
scripts/verify-package.sh passes.
scripts/public_safety_check.sh passes.

Public Boundary

Publish schemas, templates, prompts, and adapters. Do not publish hosted service secrets, private research notes, raw logs, or local machine paths.

Track record

Benchmark

21 / 22

test cases passed, vs 8 / 22 without

Adoption

Users: 1
Times used: 15

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/17/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

agentlas-ai / agentlas-os

skills/public-plugin-packaging/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/17/2026Version v3

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Public Plugin Packaging

Checklist

Public Boundary

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills