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/primeline-ai/claude-code-starter-system/system-bootnpx skills add primeline-ai/claude-code-starter-system --skill system-bootgit clone --depth 1 https://github.com/primeline-ai/claude-code-starter-systemWrote 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/primeline-ai/claude-code-starter-system/system-boot)<a href="https://agentmods.dev/skills/primeline-ai/claude-code-starter-system/system-boot"><img src="https://agentmods.dev/badge/skills/primeline-ai/claude-code-starter-system/system-boot.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 | $0.00034 | $0.01357 |
| Opus 5 | $0.00017 | $0.00678 |
| Sonnet 5 | $0.00007 | $0.00271 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
system-boot 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 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.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Boot - Context Loader + Session Guidelines
You are loading the project context for the current session. Follow these steps in order, then apply the session guidelines throughout.
Part 1: Context Loading
Step 1: Read the Memory Index
Read .claude/memory/index.json to get the active project name.
If this file does not exist, skip to the "No Memory Found" fallback at the bottom.
Step 2: Read Project State
Read .claude/memory/projects/{active}.json where {active} is the project name from Step 1.
This file contains the project goals, current phase, progress log, and any known blockers.
If this file does not exist, skip to the "No Memory Found" fallback.
Step 3: Present Context Block
Output a compact context block in this format:
Project: {name} | Phase: {phase}
Last progress: {summary of the most recent entry in the progress array}
Next step: {suggested_next from the latest progress entry, or the first unfinished goal}
Known blockers: {any blocking issues listed in the blockers field, or "none"}
Rules for the context block:
- Keep it under 200 tokens total
- Summarize progress entries - do not paste them verbatim
- If there are multiple goals, show only the primary one
- If blockers is empty or missing, show "none"
Step 4: Check for Recent Handoff
Look for the most recent file in .claude/handoffs/ (sort by filename, newest first).
If a handoff file exists:
- Read it
- Add a brief summary to the context block:
Last handoff: {date from filename} Next action: {content from the "Next Session" section of the handoff}
If no handoff files exist, skip this step.
Step 5: Ready to Work
After showing the context block, say one sentence about what you are ready to help with, based on the next step from the handoff or the latest progress entry.
Example: "Ready to continue with {next step}. What would you like to tackle first?"
Part 2: Session Guidelines
These guidelines apply throughout the entire session, not just at boot.
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 · 169 lines · 34 tokens per session scan A 2895bc4e0e41
system-boot is a skill published in the GitHub repository primeline-ai/claude-code-starter-system (5 stars, last pushed 20d ago), licensed MIT. It adds 34 tokens to every session and 1,357 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 2026-08-31.
Other skills, from other repositories
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
chronicle-skysight
Use when recent Linux desktop activity memory would help answer a question or when the user asks to inspect or control Chronicle or Skysight.
context-engineering
项目级上下文工程框架:通过 PROJECT / REQUIREMENTS / ROADMAP / STATE 四层文档 为每个任务建立结构化上下文,控制 token 预算,防止上下文腐烂, 确保跨会话连续性。与 context-lifecycle 的 L0-L3 层互补。.
error-experience-library
错误经验库:自动捕获错误模式、根因和解决方案,支持查询和反馈更新。 当遇到 build error、runtime error 或需要查找历史错误解决方案时使用。.
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…