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/xcota/pos/session-startnpx skills add xcota/pos --skill session-startgit clone --depth 1 https://github.com/xcota/posWhat 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 | $0.00017 | $0.00446 |
| Opus 5 | $0.00009 | $0.00223 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
session-start 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 3d 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.
What it actually says
/session-start — Boot Personal OS Context
Boot context for a new working session. Progressive loading: minimal at start, expand by task.
Steps
- If
state/current.mdexists, read it — what's happening across all contexts right now. If it's absent (orcontext/identity.mdstill has{{ }}placeholders), the vault isn't set up yet — don't fabricate state. Warmly tell the user, in one line: "This vault isn't set up yet — just saystartand I'll do it with you (no commands, no steps)." Then stop and let them. - Read
context/priorities.md— current focus and active work - Read
context/anti-patterns-index.md→ load the LIVE watch-list (active failure modes). Fullcontext/anti-patterns.mdis reference — pull by AP-ID when a task touches that domain. - Check if
daily/{today's date}.mdexists — read last 20 lines for today's events - Scan
state/sessions/— any active checkpoints to continue? - If the task is system architecture, agent runtime, or sync — read
context/agent-runtime.md
Output
Display a compact dashboard:
=== Personal OS ===
Focus: {top priorities from priorities.md}
State: {active contexts from current.md}
Watch: {top 3 anti-patterns to remember}
Today: {key events if daily note exists}
Checkpoint: {available session to continue, if any}
===
Rules
- Total context after boot should be 15-25K tokens, not more
- Do NOT load all of knowledge/ — only load specific files when the task demands it
- Do NOT load project context unless working on that project
- If user wants to continue a session: read the checkpoint, load its context
- After displaying dashboard, ask "What are we working on?" if not obvious
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.
- 3d ago First seen · 41 lines · 17 tokens per session scan A ad5a70534029
session-start is a skill published in the GitHub repository xcota/pos (43 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 446 once invoked, about $0.0001 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
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
rtg-knowledge-graph-mcp
Operate the Vellis RTG Knowledge Graph MCP server for agent-driven graph work. Use when an agent has RTG MCP tools such as rtgvalidategraph, rtgapplylivegraphchanges, rtgstageknowledgechanges, rtgapplymigrationcutover, rtgexecutequery, snapshots, or ledger replay, especially for schema evolution, validation recovery…
documentation-sync
Keep human documentation synchronized with canonical SysML v2 models, generated component and application views, implementation realizations, repository tooling, skills, and workflow rules. Use after model, code, generated-view, README, AGENTS, skill, command, or public behavior changes.
python-component-implementation
Implement, review, or revise Python realizations of components from accepted textual SysML v2 contracts and generated views. Use when creating or aligning Python protocols, component classes, reference implementations, implementation bindings, or black-box contract tests.
sysml-reference
Ground textual SysML v2 and KerML authoring, review, language-semantics decisions, construct selection, and official-validator diagnosis in the repository's checksum-pinned specification corpus. Use for questions or changes involving parts, references, features, actions, bindings, successions, flows, ports…
model-hygiene-review
Audit accepted SysML v2 component or application models against implementations, protocols, consumers, tests, generated evidence, predecessor contracts, and git history before proposing remediation. Use for periodic model hygiene, suspected model/implementation drift, migration-loss reviews, verification-closure…