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

Superstack Doctrine

ASecurity

A correction or standing ruling from the user — a rebuke of a working habit, "make this a rule", "always do X", "never do Y again". Mint the statute BEFORE giving the substantive reply. Also to review or amend standing law. Skip for one-off task instructions that don't outlive the turn.

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

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add debabsah/superstack --skill superstack-doctrine --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Superstack Doctrine?

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

Security grade badge for Superstack Doctrine
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/debabsah-superstack-doctrine/badge)](https://www.skillsdirectory.com/skills/debabsah-superstack-doctrine)

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

Download with Pro
Files
SKILL.md
---
name: superstack-doctrine
description: A correction or standing ruling from the user — a rebuke of a working habit, "make this a rule", "always do X", "never do Y again". Mint the statute BEFORE giving the substantive reply. Also to review or amend standing law. Skip for one-off task instructions that don't outlive the turn.
---

# superstack-doctrine

Corrections become standing law, and the law gets surfaced where habits can't be trusted to remember it. Statutes live in two books, both surfaced by the session-start hook every session: the project's (`.superstack/doctrine.md`) and the owner's personal rule book (`${CLAUDE_CONFIG_DIR:-~/.claude}/superstack-doctrine.md`), which binds in every workspace (D-49).

**Scope at minting — this project, or everywhere?** A correction about how the owner is spoken to or how their preferences are honored is personal; one about this codebase's conduct is the project's. When the correction's own words don't settle it, ask, one line. Personal statutes append to the personal book, same grammar, same `# doctrine` header on first use. Where the two books collide inside a project, the project's statute outranks the personal one.

## Minting (write-ahead)

The moment a correction or ruling lands, **write the statute before composing your substantive reply** — the reply comes second. Append to `.superstack/doctrine.md`:

```
## <YYYY-MM-DD> — <short imperative title>
> verbatim: "<the user's own words, quoted exactly>"
scope: <when this binds — the action class, not "always">
supersedes: <#none, or the dated title it replaces>
reopens-if: <the condition that would re-open this, or "none foreseen">
```

Announce the mint in one line ("statute added: <title>"). Create the file with a `# doctrine` header on first use.

## The rules of the law

- **Append-only.** Never edit or delete a statute. To change one, add a new statute citing what it supersedes — the history is the point.
- **Scope is an action class** (publishing, option menus, commit style), never "always" — an unscoped law can't be checked and won't fire.
- **A ruling without a reopen condition drifts toward dogma.** Every statute carries `reopens-if` — the observation that would make it worth re-examining; "none foreseen" is legal and honest, a blank is neither.
- **Statutes bind until the owner lifts them.** When acting inside a statute's scope, comply or escalate to the user — never silently override. A user instruction that contradicts a statute is an escalation moment: name the conflict, let them rule (that ruling is usually the next statute).
- **Mint on corrections, not preferences you infer.** A statute needs the user's words; if you only suspect a standing preference, ask — the answer is the quote.
- **Prune what never fires.** If a statute's scope hasn't occurred for months, propose retiring it at a `superstack-ship` overlay compaction — with the user, not unilaterally.

## Boundary with the overlay

Gotchas (trap → cause → rule, discovered by work) go to `.superstack/project.md` per the method's overlay protocol. Doctrine holds *the user's rulings* — the things a future session must not relitigate. When one event yields both, write both and cross-reference.

Attribution

debabsahdebabsah
View sourceMore from debabsah →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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".

1066601 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', ...

693161 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 →