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/with-geun/alive-analysisWrote 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/with-geun/alive-analysis/analysis-promote)<a href="https://agentmods.dev/commands/with-geun/alive-analysis/analysis-promote"><img src="https://agentmods.dev/badge/commands/with-geun/alive-analysis/analysis-promote.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 | $0.01225 |
| Opus 5 | $0.00000 | $0.00613 |
| Sonnet 5 | $0.00000 | $0.00245 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
analysis-promote 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 7d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/analysis promote
Promote a Quick analysis to Full when it outgrows the Quick format.
Instructions
Step 1: Identify the Quick analysis
- If argument provided (Quick ID): use that analysis
- If no argument: read
.analysis/status.mdand show active Quick analyses. Ask user which to promote. - If no Quick analyses exist: tell user "No active Quick analyses to promote."
Step 2: Assess promotion readiness
Read the Quick analysis file and evaluate whether it has outgrown the Quick format.
Auto-detection signals (AI should proactively suggest promotion when 2+ signals are present):
| Signal | Detection | Why it matters |
|---|---|---|
| Multiple hypotheses | INVESTIGATE section lists 3+ hypotheses or findings | Quick is for one focused question |
| Multiple data sources | LOOK section references 2+ distinct data sources | Data complexity exceeds Quick scope |
| Long INVESTIGATE | INVESTIGATE section exceeds ~20 lines of content | Analysis depth warrants full structure |
| Multiple audiences | VOICE section addresses 2+ distinct stakeholder groups | Communication complexity needs full VOICE |
| Follow-up spawning | EVOLVE section proposes 2+ follow-up analyses | The question is branching |
| Metric proposal | EVOLVE section has a "Proposed New Metrics" block filled | Metric definition needs full rigor |
| Scope creep noted | A "Parked Questions" section exists | The scope expanded beyond Quick |
| Data quality issue | A "Data Quality Issue" section exists | Quality issues need full documentation |
Promotion prompt:
AI: "This Quick analysis is showing signs of outgrowing the format:
- {signal 1}
- {signal 2}
Promoting to Full would give you:
- Separate files for each ALIVE stage (easier to navigate)
- Full checklists (more rigorous quality control)
- Better structure for multiple hypotheses/audiences
Want to promote it? (This keeps the original Quick file for reference)"
When NOT to promote:
- The Quick analysis is nearly done (VOICE or EVOLVE stage, wrapping up)
- The user explicitly chose Quick for speed and is OK with the trade-offs
- The "complexity" is just thorough documentation, not actual scope growth
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.
- 7d ago First seen · 111 lines · 0 tokens per session scan A d7f065766a94
analysis-promote is a command published in the GitHub repository with-geun/alive-analysis (41 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,225 tokens. 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 commands, from other repositories
next
A command that takes the next unfinished leaf item from an active project plan and runs one implementation cycle. The cycle includes implementation, verification, journal entry, and plan-status update.
project_init
A command that starts tracking a project with ocul-pm by creating its project records and agent logging rules.
standup
A command that creates a daily stand-up report from an ocul-pm project's work logs and plan. A stand-up is a short update on completed work, blocked work, and next steps.
inception
A command for starting the design of a new project or major feature area. It guides research, agreement on the specification, a detailed three-level plan, evaluation checks, and initial project rules.
optimize-listing
Optimize Shopify App Store listing for search discovery, conversion, and Built for Shopify certification requirements.
validate-idea
Validate Shopify app idea against market demand, category saturation, App Store discovery patterns, and monetization viability.