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 regen-coordination/org-os-template --skill review-promotegit clone --depth 1 https://github.com/regen-coordination/org-os-templateWrote 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/regen-coordination/org-os-template/review-promote)<a href="https://agentmods.dev/skills/regen-coordination/org-os-template/review-promote"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/review-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/regen-coordination/org-os-template/review-promote"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/review-promote.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 | $0.00054 | $0.00710 |
| Opus 5 | $0.00027 | $0.00355 |
| Sonnet 5 | $0.00011 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
review-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 11d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-promote
The human gate. You facilitate; the human decides. You NEVER promote without a named reviewer in the room.
Session loop
CLI entrypoint: node <framework>/src/cli.mjs (abbreviated … below). Run from
the instance dir so kms.yaml defaults and stored refs resolve.
… review list --adapter <a> --target <t>— show the queue, grouped by schema.- For each object (or the slice the reviewer picks): present it whole — title, fields, provenance chain (origin → work_order → source_lineage). Flag anything the accept gate can't judge: unverified claims, thin provenance, Frame-1 language (see csis-review), high-risk triggers missed at ingest.
- Ask the reviewer for the verdict. The honest menu (real K1 maturity rungs —
there is no "plausible"):
- stays
raw(not ready) ·draft(shaped but unchecked) ·candidate(sane, awaiting verification) ·source-linked(claims traced to sources) ·reviewed(human checked it) · or edit first (fix fields, then promote).
- stays
… review promote <ref> --maturity <value> --reviewer <name>— one object at a time. The CLI validates the merged object BEFORE writing (a refused promotion writes nothing), clearsai_assistedon any reviewer-present promotion (provenance.authorship keeps the AI history), and re-derives the index.- Refused by invariants? The message names the conflict — usually a
structural field must move first (e.g. a demotion to
rawwhilepublic_useis stillreviewed-for-*: resetpublic_usevia the "edit first" path, then demote). Loop back to step 3.
- Refused by invariants? The message names the conflict — usually a
structural field must move first (e.g. a demotion to
- Demotion (
--maturity raw, no reviewer needed): the CLI leaves oldreviewed_by/last_reviewedstamps in place as history — record WHY in the object'snotesfield (edit before demoting) so the trail is honest. - End of session: report — N reviewed, M promoted, K sent back with notes.
Hard rules
- No reviewer present → read-only session. Summarize the queue; promote nothing.
- Never batch-promote. Each object is a decision.
- Promotion to
reviewedof MRV/carbon/funding/governance claims additionally needs the csis-review skill's high-risk pass — point the reviewer there. ai_assistedclears on ANY reviewer-present promotion (even todraft) — if the reviewer only skimmed, promote todraft/candidatehonestly rather thanreviewed; the flag-clear means "a named human now answers for this".
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.
- 11d ago First seen · 51 lines · 54 tokens per session scan A b3f6fa0a4d14
review-promote is a skill published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 710 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
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.