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

Drift Sweep

ASecurity

Bootstrap or audit a repository documentation contract, classify Markdown truth surfaces, migrate shadow trackers to GitHub issues, and reconcile stale operational facts. Use when the user says drift sweep, asks whether docs are stale, retires or renames a process, wants a .doc-contract, or is preparing a launch.

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsrailsgitdocumentation

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add jckeen/dotfiles --skill drift-sweep --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Drift Sweep?

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

Security grade badge for Drift Sweep
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jckeen-drift-sweep/badge)](https://www.skillsdirectory.com/skills/jckeen-drift-sweep)

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

Download Zip
Files
SKILL.md
---
name: drift-sweep
description: Bootstrap or audit a repository documentation contract, classify Markdown truth surfaces, migrate shadow trackers to GitHub issues, and reconcile stale operational facts. Use when the user says drift sweep, asks whether docs are stale, retires or renames a process, wants a .doc-contract, or is preparing a launch.
---

# Drift Sweep

Work in the current repository. Read ADR 0005 in the dotfiles repository when
available. Use bootstrap mode when `.doc-contract` is absent and sweep mode when
it exists.

The contract format is `LIVING|GENERATED|SOURCE|HISTORICAL <glob>` with first
match winning, plus optional `BANNED[:TIER,TIER] <regex>` guards.

## Bootstrap

1. Inventory tracked Markdown with `git ls-files '*.md'` and propose a tier for
   each file:
   - `LIVING`: maintained by normal product or release work; keep this set small.
   - `GENERATED`: produced or asserted by scripts or CI.
   - `SOURCE`: Markdown used as configuration, skills, templates, or rules.
   - `HISTORICAL`: point-in-time plans, audits, reviews, and retired records.
2. Present the classification before writing it. Prefer deleting stale guidance
   over declaring it living.
3. Migrate shadow trackers instead of tiering them. Move genuine open work into
   GitHub issues, preserve worthwhile completed history in the changelog, then
   delete or mark the old tracker historical.
4. Ask for retired names, domains, and hosts that should become `BANNED` guards.
   Propose a no-unchecked-checkbox guard for living/generated docs unless the
   repository intentionally ships active checklists.
5. Write `.doc-contract`. Add the standard dated historical banner near the top
   of historical files that lack an ADR-style status/date header.
6. Vendor `check-doc-truth.sh` from the dotfiles scripts into the repository's
   script directory and wire it into existing CI.
7. Run the checker and fix dead references, banned facts, and authoritative
   links to retired sources. Search for prose that still calls newly historical
   material the system of record or canonical tracker.
8. Ship the contract, checker, CI wiring, and fixes together through the
   repository's normal PR workflow.

## Sweep

1. Run the vendored checker and collect every violation.
2. Compare issue references in living/generated docs against current GitHub
   issue state.
3. Compare documented migration or schema high-water marks against canonical
   migration directories.
4. Inspect stale PRs and ghost worktrees. Do not delete branches or worktrees
   with unique or unintegrated work.
5. Fix verified drift in one small documentation change, or report `clean` when
   nothing is stale.

## Guardrails

- Never fabricate history or backfill a retired ledger.
- Never create another tracker file to replace a stale tracker.
- Never hardcode an unstable count, SHA, version, or host in prose when CI
  cannot assert it.
- Treat issue creation, branch deletion, and publication according to the
  repository's authorization rules; do not infer broader external authority.

Attribution

jckeenjckeen
View sourceMore from jckeen →
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 →