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 skills add wrg32786/aigent-os --skill promotegit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/promote)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/promote"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/promote/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/skills/wrg32786/aigent-os/promote"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/promote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01208 |
| Opus 5 | $0.00034 | $0.00604 |
| Sonnet 5 | $0.00014 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote
The conversation is a substrate. Most of what happens in it is ephemeral — task-specific, session-bound, useful in the moment and gone after. But some exchanges produce durable insights: a new architectural understanding, a person fact worth remembering, a doctrine pattern emerging, a decision that should be logged.
Without /promote, those insights live in the conversation transcript and decay. With /promote, the principal can elevate them to vault content the framework will surface in future sessions.
When to use
- The conversation produced an insight that should outlive this session
- The principal said "we should remember that" or "make a note that…"
- A doctrine pattern is starting to emerge from the discussion
- A new person, project, or concept came up that needs a vault entry
- Triggered by Caddy on prompts like: "/promote", "promote that", "make a note that", "save that insight", "elevate to doctrine", "capture this conversation", "remember that we decided", "this should be a vault note"
How to execute
Step 1 — Identify the slice to promote
Ask: which part of the conversation should become durable?
If the principal points to specific turns ("the last 10 messages about X"), use those. Otherwise:
- Default to the last 5-10 turns AND any explicitly-referenced earlier exchanges
- If unclear, ask one focused question: "Promote the {topic A} discussion or the {topic B} discussion?"
Step 2 — Categorize the artifact
Map the slice to a vault category:
| If the slice is about... | Promote to... |
|---|---|
| A new concept, doctrine, or pattern | vault/concepts/{slug}.md |
| A person (collaborator, advisor, contact) | vault/people/{name}.md |
| A project (current or new) | vault/projects/{slug}.md |
| A decision with reasoning | append entry to vault/memory/DECISION_LOG.md |
| A learning sweep on a tool/framework | vault/concepts/learning/{slug}.md (use /learn instead) |
| A person/process rejection with reasoning | append entry to vault/concepts/What I Am Not Building.md |
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 · 113 lines · 68 tokens per session scan A 65ae0a826230
Promote is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,208 once invoked, about $0.0003 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 2026-09-01.
Other skills, from other repositories
chief-of-staff
Skill "chief-of-staff" from aimerdoux/wavex-os, covering 🧭 chief of staff, 🧠 your identity & memory, 🎯 your core mission, 💭 your communication style and 🚨 critical rules you must follow.
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
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…
send-email
Compose and send a one-off email to a named recipient via Resend - written in the operator's voice, then sent in-run through the shared send caps with an operator audit copy.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.