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.
git clone --depth 1 https://github.com/AI-Native-Systems/north-star-advisorWrote 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/commands/ai-native-systems/north-star-advisor/resume)<a href="https://agentmods.dev/commands/ai-native-systems/north-star-advisor/resume"><img src="https://agentmods.dev/badge/commands/ai-native-systems/north-star-advisor/resume/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ai-native-systems/north-star-advisor/resume"><img src="https://agentmods.dev/badge/commands/ai-native-systems/north-star-advisor/resume.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00009 | $0.03616 |
| Opus 5 | $0.00005 | $0.01808 |
| Sonnet 5 | $0.00002 | $0.00723 |
| Haiku 4.5 | $0.00001 | $0.00362 |
Grade A, and why
resume 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 9d 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 — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/northstar:resume
Resume generation from the last checkpoint after interruption.
FIRST: Read State (REQUIRED)
BEFORE ANY OTHER ACTION:
1. Read: north-star-advisor/.work-in-progress/state.json
2. **Legacy state check:** If state.json contains "completed_phases" (pre-2.0.0 format):
- Go to Legacy State Detection section (Step L1)
- Do NOT continue into normal workflow
- Do NOT write any flag updates to state.json
3. Get: plugin_index_path from state.json
4. Read: templates/index.yml at that exact path
If plugin_index_path is missing from state.json:
- Glob:
**/northstar/**/templates/index.yml - If exactly 1 match: update state.json with found path
- If 0 matches: display "Could not locate
templates/index.ymlfrom cached state or fallback glob." and stop - If multiple matches:
- List all found paths
- Use
AskUserQuestionwith each path as an option - Stop and wait for the user's selection
- Store selected path in state.json as
plugin_index_path - Then continue
Rules:
- NEVER hallucinate document names - only use names from index.yml
- ALWAYS use plugin_index_path from state.json
- Filter templates by
state.uxandstate.deepbooleans
Arguments
/northstar:resume [options]
| Option | Description |
|---|---|
--ux |
Add UX templates. Updates state.json. |
--deep |
Add deep architecture templates. Updates state.json. |
--full |
Enable all templates (--ux + --deep). Updates state.json. |
--search-tool <tool> |
Override search tool. Updates state.json. |
--restart |
Restart current template from scratch |
--rollback |
Go back to previous template |
--checkpoint <name> |
Resume from specific checkpoint |
Prerequisites
- Project must be initialized with
/northstar:advisor - At least one checkpoint must exist in
north-star-advisor/.work-in-progress/checkpoints/, OR legacy v1.x state is detected (handled via Legacy State Detection)
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.
- 9d ago First seen · 486 lines · 9 tokens per session scan A 4ebf6c8bc746
resume is a command published in the GitHub repository AI-Native-Systems/north-star-advisor (7 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 3,616 once invoked, about $0.0000 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 commands, from other repositories
release
Guided release for the skill-engine repo. Bumps the six version surfaces, drafts the CHANGELOG entry, runs validators, then pauses for the maintainer to commit, push, and tag manually. Accepts major / minor / patch / explicit X.Y.Z.
adr
Generate a well-formed Architecture Decision Record from a change in context — Status / Context / Decision / Consequences. One-shot helper, off-spine.
changelog
Draft a Keep a Changelog–style entry (Added / Changed / Fixed / Removed) from commits since the last tag. Standalone helper — does not replace /ship's release step.
pr-describe
Draft a PR description (summary / what changed / test plan) from the branch's commits and diff against the base branch. Off-spine helper, no agents.
init
Install the formatters this repository needs, with every command visible before it runs.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.