Khaos-Brain: Skill for Codex

.agents/skills/organization-review/SKILL.md

organization-review is a skill for Codex from liuyingxuvka/Khaos-Brain. It costs 63 tokens per session (733 once invoked), scanned A, original, MIT.

A review workflow for proposed changes to an organization knowledge base, including cards, skills, evidence, privacy, and GitHub merge readiness. A knowledge base is a shared collection of information for future work.

In plain words
What is it for?
Use it to approve, reject, merge, split, rewrite, promote, demote, deprecate, or cross-link organization knowledge-base changes.
Why use it?
It helps reviewers judge the complete change and its supporting evidence, rather than approving an isolated file without checking safety or provenance.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is liuyingxuvka/Khaos-Brain's own configuration. It tells Codex how to work on Khaos-Brain itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Khaos-Brain configures →

Reuse

Borrowing it

Nothing to install: this file belongs to liuyingxuvka/Khaos-Brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/liuyingxuvka/Khaos-Brain/main/.agents/skills/organization-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/liuyingxuvka/Khaos-Brain

Made for: Codex.

Wrote 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.

agentmods badge for organization-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/liuyingxuvka/khaos-brain/organization-review/github.svg)](https://agentmods.dev/skills/liuyingxuvka/khaos-brain/organization-review)
Your own site
<a href="https://agentmods.dev/skills/liuyingxuvka/khaos-brain/organization-review"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/khaos-brain/organization-review/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.

agentmods 80×15 button for organization-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/liuyingxuvka/khaos-brain/organization-review"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/khaos-brain/organization-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 733 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00733
Opus 5 $0.00032 $0.00367
Sonnet 5 $0.00013 $0.00147
Haiku 4.5 $0.00006 $0.00073

Measured 12d ago against content hash f7065cc550b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

organization-review 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 12d 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.

.agents/skills/organization-review/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Organization Review

Use this Skill when reviewing organization KB changes or running full organization maintenance automation. It is guidance for judgment, not a hard apply gate for ordinary organization Sleep maintenance.

Review Contract

Treat the review unit as a bundle, not a standalone file:

  • import candidate, main card change, or Skill-linked card bundle;
  • declared Skill dependency or Skill registry change;
  • task evidence and provenance;
  • privacy and sharing policy impact;
  • GitHub merge path and rollback story.

Do not approve a Skill only because it exists. A Skill becomes organization knowledge only when cards explain when it is useful, what outcome it predicts, what hard-stop behavior applies when its required Skill is unavailable, and what evidence supports it.

Treat the organization KB as a shared exchange layer, not as a central truth layer. Organization main cards may be maintained with the same editorial posture as local Sleep: keep, reject, watch, merge, split, rewrite, promote, demote, deprecate, or cross-link when evidence supports the decision. Do not reject a card-content change merely because the target is already in main or already trusted; instead review the evidence, privacy boundary, usefulness, and rollback story.

Required Checks

  1. Validate the organization repository manifest and expected paths.
  2. Confirm changed paths match the intended merge lane.
  3. Reject raw private preferences, credentials, tokens, local absolute paths, hardware identifiers, or user-specific interaction memories.
  4. For cards, check that scenario, action, prediction, confidence, route, and operational use are organization-reusable.
  5. For Skill dependencies, check that each dependency is required, recommended, or optional and has evidence from one or more cards.
  6. For card-bound Skill bundles, require bundle_id, content_hash, version_time, original_author, read-only import behavior, and update_policy: original_author_only.
  7. For same-bundle_id updates, approve only original-author updates and use version_time to select the latest approved version; non-author changes must fork to a new bundle_id.
  8. For approved Skills, require a pinned version or version time and sha256: content hash.
  9. Do not auto-install or recommend auto-install for candidate, rejected, unknown, or unpinned Skills.
  10. Treat main card content maintenance as in scope for organization Sleep when evidence supports it. Keep privacy, registry, policy, organization-review Skill changes, and executable Skill changes under stricter review.
  11. Record rejection reasons when a bundle is weak, unsafe, private, too local, duplicated, or missing evidence.
  12. Keep the output reviewable: summarize accepted changes, rejected changes, unresolved risks, checks run, and the exact GitHub branch or PR path.

Read the full file on GitHub · 70 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 70 lines · 63 tokens per session scan A f7065cc550b2

Subscribe to this mod's changes

organization-review is a skill published in the GitHub repository liuyingxuvka/Khaos-Brain (37 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 733 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 2026-08-30.

Related

Other skills, from other repositories

knowledge-base

Skill "knowledge-base" from Pinvou/pinvou-agent, covering ima knowledge base, operations, routing rules, examples and file upload guard.

Pinvou/pinvou-agent · 0 tokens

notes

Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.

Pinvou/pinvou-agent · 0 tokens

shodh-memory

Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.

varun29ankuS/shodh-memory · 53 tokens

vault

Search, read, write, and manage files in the Kept conversation vault. Use when the user asks about past conversations, wants to save notes, needs to find specific content, or wants to organize their vault.

egroup-labs/kept · 45 tokens

knowledge-ingestion

A skill for saving links, social posts, videos, podcasts, screenshots, PDFs, local files, or text into an Obsidian knowledge base, a personal collection of searchable notes. The ingestion tools analyse and format the material for storage.

lyc403223157-source/knowledge-inbox · 112 tokens

personal-knowledge-ingestion

A skill for saving links, videos, social posts, local files, screenshots, PDFs, or text into an Obsidian vault, a folder used for personal notes and knowledge. It uses connected knowledge tools to process and format the saved item.

lyc403223157-source/knowledge-inbox · 86 tokens