Agentlas OS is a local-first system for creating, storing, borrowing, and running specialist AI agents and temporary agent teams through supported hosts and models. It serves people who want reusable agents that remain available across computers and model workspaces, and the catalogue contains its skills, commands, hooks, agents, instructions, plugin, and rule.
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/agentlas-ai/agentlas-os/agentlas-packagingnpx skills add agentlas-ai/Agentlas-OS --skill agentlas-packaginggit clone --depth 1 https://github.com/agentlas-ai/Agentlas-OSWrote 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/agentlas-ai/agentlas-os/agentlas-packaging)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-os/agentlas-packaging"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-os/agentlas-packaging.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00739 |
| Opus 5 | $0.00023 | $0.00369 |
| Sonnet 5 | $0.00009 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
agentlas-packaging 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 6d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentlas Packaging
Procedure
- Inspect the existing source: prompt, repo, ZIP, runtime folder, skill, command, or generated agent package.
- Classify it as single-agent, team-builder, or mixed/unclear.
- Run
contracts/builder-interview-research-gate.mdwhen the source behavior, target user, tools/plugins, output artifacts, or evaluation bar are unclear. Packaging must not turn a shallow prompt into a polished but weak package. When the gate runs, research official sources, similar agent repositories or comparables, academic/professional theory, and plugin docs before changing the source behavior. - Preserve useful behavior while adding Agentlas contracts:
AGENTS.md;docs/builder-interview.md;docs/research-sources.md;docs/tool-selection.md;docs/domain-expert-synthesis.md;docs/prompt-performance-contract.md;.agentlas/capability-eval-plan.json;.agentlas/agent-card.json;.agentlas/company-blueprint.json;.agentlas/mode-map.json;.agentlas/memory-map.json;.agentlas/memory-tickets.jsonl;.agentlas/vault-references.json;.agentlas/global-commands.json;- runtime adapters;
- verification scripts.
- Author the workforce résumé block on the routing card (
workforceon.agentlas/agent-card.json/ the marketplace routing card). The hub Workforce search matches on exactly these fields; a card without them is invisible to every WorkOrder that uses them, andcard lintblocksrouting_readywithout the block. Use the versioned ontology graph contract (agentlas_cloud/workforce/ontology_v1.json, awo:2026-07-15.2) for seed aliases and relation semantics, never as an allowlist:roles: 0-4 openrole:*professional-responsibility ids;communities: 1-5 opencommunity:*professional-domain ids;skills: 3-12 openskill:*verb-object capability ids;knowledge: openknowledge:*domain/method ids backed by the package;modalities: optional non-text input/output metadata;languages: optional genuine delivery languages, never listing locales. New well-formed semantic IDs are valid graph concepts and must not be rejected merely because the seed snapshot has not seen them before.
- Add or repair the global command across Claude Code, Codex, Gemini CLI, generic AGENTS.md tools, and terminal adapters.
- Remove secrets, raw logs, private local notes, and unsafe public paths.
- Run
scripts/verify-team-package.sh <package-root>after repair. If it fails, correct the package shape before any final handoff. - Run package verification and public-safety checks before release.
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.
- 6d ago First seen · 62 lines · 46 tokens per session scan A 7f33da2b197b
agentlas-packaging is a skill published in the GitHub repository agentlas-ai/Agentlas-OS (1,101 stars, last pushed 3d ago), licensed Apache-2.0. It adds 46 tokens to every session and 739 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
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
performance-optimization
Measure-first performance work. Use on triggers like "it's slow", "profile this", "optimize perf", "fix the bottleneck", "improve load time / Core Web Vitals", or when a measured regression needs fixing. Enforces measure-before-optimize. Fills a perf gap not covered by existing project skills. Not a build/ship…
scenario-design
Draft real-life test SCENARIOS (not smoke tests) from a change/feature spec. Derives edge-case, performance, frontend-quirk and error-handling scenarios with ISTQB techniques, routes each to a test level, and writes test-plan.md, emitting clarification questions on a spec gap. Use on "design test scenarios", "what…
plan-proposal
Develop-side planning orchestrator for an OpenSpec change: artifact creation → doubt-driven-review → scenario-design → fold of automated scenarios into tasks.md, then STOPS at the git-worktree boundary. Main interactive session only; never a subagent. Triggers: "plan this change", "draft the proposal and plan"…