Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Raw

ASecurity

**The compliance track is blocked on us, not on Aldergate: send the architecture diagram today and get a dated commitment from Okafor directly — three of the four open items can't move until those two things happen.** **What is already answered (treat as settled, don't re-ask)** - A security review before production is mandatory, and a penetration test may be added inside it — so the build price cannot be fixed to a scope until the review is underway (Q1, Q2; R-07 open since 3 May). - Buildin...

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentssecurity

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add welltraum/minto --skill raw --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Raw?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Raw
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/welltraum-raw-ff1987e0/badge)](https://www.skillsdirectory.com/skills/welltraum-raw-ff1987e0)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
01-big-chief__codex__control.md
**The compliance track is blocked on us, not on Aldergate: send the architecture diagram today and get a dated commitment from Okafor directly — three of the four open items can't move until those two things happen.**

**What is already answered (treat as settled, don't re-ask)**
- A security review before production is mandatory, and a penetration test may be added inside it — so the build price cannot be fixed to a scope until the review is underway (Q1, Q2; R-07 open since 3 May).
- Building to Aldergate's internal hardening framework will not buy an exemption; the review happens regardless (Q2).
- Dependencies are judged inside the review, not pre-approved one by one, and there is no turnaround commitment we can plan against (Q4, Q5).
- Work from Ireland is permitted (Q6).

**What still has to be obtained — in the order it blocks us**
1. **Data storage, encryption and logging requirements (Q7).** Declined pending an architecture diagram. Our draft has existed since 11 August and has not been sent (R-14). This is the only blocker fully in our hands.
2. **A ruling on Lisbon.** Only Ireland was ever approved. The PM raised the two Lisbon-based engineers on 9 July and Aldergate did not respond — silence, not consent. This is not on the risk register and should be.
3. **The approved-package list.** Promised 12 May by Mercer, again 9 July by Whitcombe, still absent at 98 days with no date attached (Q3, R-11). Two owners, no deadline.
4. **Direct access to S. Okafor.** The information security owner has never attended a joint meeting; everything routes through Whitcombe. Every item above depends on a decision only Okafor can make.

**What to do today**
- Send the 11 August draft architecture diagram to Whitcombe and Okafor together, closing R-14 and putting Q7 in play.
- Ask in the same message for a dated commitment on the package list and a written answer on Lisbon — naming both dates you need.
- Add a Lisbon-location risk row to the register; keep R-07 open and flag to the client that build-phase pricing stays indicative until review scope is known.

```mermaid
flowchart TD
    A["Blocked on us: send the diagram and reach Okafor directly"] --> B1["4 answers are settled — stop re-asking"]
    A --> B2["4 items outstanding, 1 of them ours"]
    A --> B3["3 moves today"]
    B1 --> C11["Review mandatory, framework buys no exemption, no dependency SLA, Ireland OK"]
    B2 --> C21["Q7 waits on our 11 Aug diagram (R-14)"]
    B2 --> C22["Lisbon unanswered since 9 Jul; not on register"]
    B2 --> C23["Package list 98 days late, two owners, no date (R-11)"]
    B2 --> C24["Okafor never in the room"]
    B3 --> C31["Diagram out; dated asks on list + Lisbon; price stays indicative (R-07)"]
```

Attribution

welltraumwelltraum
View sourceMore from welltraum →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →