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/r5rana/agentware/onboardingnpx skills add r5rana/agentware --skill onboardinggit clone --depth 1 https://github.com/r5rana/agentwareWrote 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/r5rana/agentware/onboarding)<a href="https://agentmods.dev/skills/r5rana/agentware/onboarding"><img src="https://agentmods.dev/badge/skills/r5rana/agentware/onboarding.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 | $0.00000 | $0.12196 |
| Opus 5 | $0.00000 | $0.06098 |
| Sonnet 5 | $0.00000 | $0.02439 |
| Haiku 4.5 | $0.00000 | $0.01220 |
Grade B, and why
onboarding scanned grade B with 2 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 5d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
helpful. Don't lecture, don't pad. The user came here to do work; onboarding is Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s http://localhost:1234/v1/models`) — see the feature's How it starts
The opening of the file, as written. The whole thing — 852 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding Skill — agentware First-Run Flow
When to invoke: when the external knowledge directory is not yet configured, OR its
.initializedsentinel does not exist. Resolve the dir withscripts/agentware config --knowledge-dir-only. This is a one-time procedure per operator. Once it finishes, the sentinel is written and this skill never runs again for this instance.
agentware ships as a generic, personal-data-free steering framework. The repo contains ONLY the steering: methodology, agents, skills, the loop runner, and the deterministic toolkit. It contains no knowledge base. Onboarding is the flow that asks the operator where to keep their knowledge base, creates it OUTSIDE the repo, and personalizes it. The same clone works for anyone — each operator points it at their own knowledge directory.
It is interactive — the agent talks to the user, asks where to store knowledge, investigates the system (read-only), introspects agentware itself, then writes the knowledge base into the external directory.
The core design (state this to the user)
- This repo is pure steering. Nothing personal is ever committed to it.
- The knowledge base lives in a directory you choose, outside this repo
(e.g.
~/agentware-knowledgeor anywhere you like). It holds your profile, projects, learnings, and configs. - The repo finds your knowledge dir via
~/.agentware/config.envor theAGENTWARE_KNOWLEDGE_DIRenvironment variable. - Because the path is external and the config lives in HOME, you can push this repo publicly and share it — the clone is generic and stays read-only as you work.
- Everything mutable goes to your dir: knowledge, learnings, agent-created skills,
per-feature work (
work/), AND a full audit log (logs/) — every prompt you send and every session transcript, timestamped, so you never lose anything. This logging is automatic via Claude Code hooks; no action needed from you.
Self-extension clause (always true)
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.
- 5d ago First seen · 852 lines · 0 tokens per session scan B 0d71ce24acbb
onboarding is a skill published in the GitHub repository r5rana/agentware (24 stars, last pushed 18d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 12,196 tokens. A static security scan graded it B with 2 findings (strips warnings and disclaimers, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
Migrate
Intakes external content, classifies chunks against LifeOS taxonomy, commits with provenance. Sources: .md/.txt, stdin, LifeOS dirs, CLAUDE.md/Cursor/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports. MigrateScan classifies → routing table. MigrateApprove with…
release
Cut a versioned release and publish everos to PyPI via the tag-triggered workflow.
personal-assistant
A personalized assistant that remembers your preferences.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…