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
  • 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.

Back to skills

Brig Builder

ASecurity

Execute a plan file in 1-2 file steps with green tests and receipt lines

54 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agents

Works with

terminal

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add fordaaaa/panoply --skill brig-builder --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Brig Builder?

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

Security grade badge for Brig Builder
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fordaaaa-brig-builder-panoply/badge)](https://www.skillsdirectory.com/skills/fordaaaa-brig-builder-panoply)

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

Download Zip
Files
SKILL.md
---
name: brig-builder
description: Execute a plan file in 1-2 file steps with green tests and receipt lines
---

Use this when a plan file exists and authorizes the change. Execute the plan,
nothing else.

## Input

A plan file (e.g. `plans/<task>.md` or `.panoply/specs/<slug>.md`).
Do not start without one. The plan's "files in scope" is authoritative.

## Procedure

1. Read the plan file fully before touching code.
2. Work in steps of **1–2 files max per step**.
3. After each step, run the plan's verification command — it must be green
   before continuing. Use the repo's own runner (see `polyglot` skill);
   never assume one exists.
4. End every change with a receipt line:

```text
path:line-range — change
```

## Rules

- Execute only what the plan authorizes. No drive-by refactors,
  no out-of-scope files, no new dependencies the plan did not approve.
- Byte offsets from the index are authoritative; never guess spans.
- Run `blast_radius` before edits and `check_refs` before deletes.

## Terminal refusal lines

Copy exactly. These end the step — do not work around them:

```text
too-big. split:
```

```text
needs-confirm. op:
```

```text
ambiguous. ask:
```

Use `too-big. split:` when a step would exceed 2 files — name the proposed
split after the prefix. Use `needs-confirm. op:` before any destructive or
out-of-scope operation — name it after the prefix. Use `ambiguous. ask:`
when the plan contradicts itself or underspecifies the change — state the
question after the prefix.

## Handoff

Output is the diff plus receipt lines. The reviewer verifies the diff
against the plan file line by line.

Attribution

fordaaaafordaaaa
View sourceMore from fordaaaa →
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".

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', ...

686011 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.

651 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 →