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 a repo's doc contract or audit doc drift — declares every markdown surface (LIVING/GENERATED/SOURCE/HISTORICAL), wires the CI doc-truth checker, migrates shadow trackers to GitHub issues, and reconciles out-of-band drift (closed issues, migration high-water marks, stale PRs, ghost worktrees). Use when the user says "drift sweep", "bootstrap the doc contract", "are these docs stale", after a rename or process retirement, or pre-launch.

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

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-dotfiles/badge)](https://www.skillsdirectory.com/skills/jckeen-drift-sweep-dotfiles)

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

Download Zip
Files
SKILL.md
---
name: drift-sweep
description: Bootstrap a repo's doc contract or audit doc drift — declares every markdown surface (LIVING/GENERATED/SOURCE/HISTORICAL), wires the CI doc-truth checker, migrates shadow trackers to GitHub issues, and reconciles out-of-band drift (closed issues, migration high-water marks, stale PRs, ghost worktrees). Use when the user says "drift sweep", "bootstrap the doc contract", "are these docs stale", after a rename or process retirement, or pre-launch.
---

Work in the current repo. Mode is auto-detected: no `.doc-contract` at the
repo root → **Bootstrap**; contract present → **Sweep**.

Spec: ADR 0005 in dotfiles (`docs/adr/0005-doc-contract-drift-prevention.md`).
Contract format: `LIVING|GENERATED|SOURCE|HISTORICAL <glob>` (first match
wins) and `BANNED[:TIER,TIER] <regex>` guard lines.

## Bootstrap mode

1. Inventory: `git ls-files '*.md'`. For each file propose a tier:
   - **LIVING** — updated as a side effect of merges (README, CHANGELOG,
     maintained guides). Keep this list small; prefer deleting a stale doc
     over declaring it.
   - **GENERATED** — produced or asserted by CI/scripts.
   - **SOURCE** — markdown-as-config: skill/agent definitions, templates,
     rule files.
   - **HISTORICAL** — point-in-time records: old audits, dated reviews,
     retired ledgers, plans, ADRs.
   Present the table to the user for confirmation before writing anything.
2. **Shadow trackers get migrated, not tiered.** A checkbox/TODO file
   (TODO.md, LAUNCH_CHECKLIST.md, or any file whose substance is open work
   items): for each open item run
   `gh issue create --title "<item>" --body "Migrated from <file> by drift-sweep"`;
   move closed items worth keeping into CHANGELOG.md. Then delete the file,
   or mark it HISTORICAL if the user wants the record kept.
3. Ask the user for old names, parked domains, and retired hosts; add a
   `BANNED <regex>` line per answer. Propose the checkbox guard
   `BANNED:LIVING,GENERATED ^[[:space:]]*[-*] \[ \]` by default (omit if the repo
   legitimately ships checklists in active docs).
4. Write `.doc-contract` at the repo root.
5. Add the banner to each HISTORICAL file missing one, as a quote line in
   the first 5 lines:
   `> **Historical** — point-in-time record (<today>). Do not act on this.`
   Files with ADR-style `**Status:**` + `**Date:**` headers already pass.
6. Vendor the checker: copy `~/.claude/scripts/check-doc-truth.sh` into the
   repo's script directory (e.g. `scripts/check-doc-truth.sh`), `chmod +x`,
   and wire a CI step that runs it (a job/step in the repo's existing CI
   workflow; create a minimal workflow if the repo has none).
7. Run the checker; fix every violation:
   - dead-ref → fix the path if the target moved; replace the link with
     backticked plain text if the target is gone.
   - banned → repoint prose at the canonical source (a file, a script, the
     live command output) instead of the hardcoded fact.
   - Retirement protocol: for anything newly marked HISTORICAL, run
     `rg -il "system of record|single source of truth|canonical tracker"`
     and repoint every doc that bills the dead thing as authoritative.
8. Ship one PR: contract + vendored checker + CI wiring + all fixes.
   End with a summary of ≤10 lines.

## Sweep mode

1. Run the repo's vendored `check-doc-truth.sh`; collect violations.
2. Out-of-band reconciliation (the gap CI can't see):
   - `gh issue list --state all --limit 200` vs every issue-number mention
     in LIVING/GENERATED docs — fix stale open/closed language.
   - If docs cite a migration/schema high-water mark, compare it against the
     migrations directory (e.g. `prisma/migrations`, `supabase/migrations`).
   - `gh pr list` — surface any PR open >48h with its review + CI state.
   - `git worktree list` — prune ghost worktrees; delete local branches with
     no unique commits (`git branch --merged <default>`).
3. Fix doc items in one small docs PR. End with a ≤10-line summary — or
   just "clean" if nothing drifted.

## Never

- Backfill dead ledgers or fabricate history — banner + repoint and move on.
- Create a new tracker file to fix tracker drift — GitHub issues are the
  only open-work tracker.
- Hardcode a count, SHA, host, or version in prose — point at the canonical
  source CI can assert.

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 →