ralphctl: Skill for Claude Code

.claude/skills/drift-sweep/SKILL.md

drift-sweep is a skill for Claude Code from lukas-grigis/ralphctl. It costs 181 tokens per session (1,571 once invoked), scanned A, original, MIT.

A development skill that checks the ralphctl project’s agent files and documentation against the actual source code. It looks for stale versions, dead paths, removed names, missing environment variables, and made-up references.

In plain words
What is it for?
Use it to audit or refresh `.claude/` files and `CLAUDE.md`, especially before releases or after moving, renaming, or removing source-code items.
Why use it?
Agent instructions can quietly become outdated as code changes, causing later sessions to follow paths or rules that no longer exist.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is lukas-grigis/ralphctl's own configuration. It tells Claude Code how to work on ralphctl itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ralphctl configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lukas-grigis/ralphctl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lukas-grigis/ralphctl/main/.claude/skills/drift-sweep/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lukas-grigis/ralphctl

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for drift-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/drift-sweep.svg)](https://agentmods.dev/skills/lukas-grigis/ralphctl/drift-sweep)
Your own site
<a href="https://agentmods.dev/skills/lukas-grigis/ralphctl/drift-sweep"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/drift-sweep.svg" alt="Measured on agentmods" height="20"></a>
Per session 181 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00181 $0.01571
Opus 5 $0.00090 $0.00785
Sonnet 5 $0.00036 $0.00314
Haiku 4.5 $0.00018 $0.00157

Measured 7d ago against content hash ac860cf3f165, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

drift-sweep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/sweep.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/drift-sweep/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Sweep

The .claude/ agent and doc files mirror the shape of src/ — module paths, symbol names, env vars, command names, version numbers. The code moves every day; these mirrors do not move with it unless someone makes them. The result is silent drift: an agent confidently points the next session at runtime/mount.tsx (deleted), a doc cites RALPHCTL_JSON (never shipped), every agent hardcodes v0.7.0 while the repo is at 0.12.x. None of it fails a test, so nothing catches it — until a session follows a dead pointer and wastes a turn, or a contributor trusts a stale acceptance criterion.

This skill is the cheap, repeatable counter-pressure: a mechanical sweep that surfaces candidates, followed by judgement to confirm them. It is deliberately conservative — a false "this is drift" wastes a fix; a missed one rots quietly. So the script flags, and you verify.

When this earns its keep

  • Someone asks to audit, refresh, or clean up .claude/ or CLAUDE.md.
  • Before a release — stale version stamps and dead paths shipping in docs is avoidable.
  • Right after a rename/move under src/ (a sibling renamed, a file relocated, a symbol dropped) — the agent and doc files that named the old shape are now wrong.

How to run it

  1. Run the sweep harness to get the candidate list:

    bash .claude/skills/drift-sweep/scripts/sweep.sh
    

    It scans CLAUDE.md, .claude/agents/, .claude/docs/, and .claude/skills/ (markdown only) and prints candidates grouped into five buckets:

    • [1] Version stamps — every vX.Y.Z vs package.json. Noise is expected here: external tool versions (Claude Code, Copilot CLI) and historical migration notes (v0.6.x → …) are legitimately pinned. A bare current-feature stamp like v0.7.0 in a "this is how it works today" sentence is the real target.
    • [2] Missing paths — referenced src/, tests/, scripts/ files/dirs that no longer exist. Highest signal; a gone path is almost always real drift.
    • [3] Unread env varsRALPHCTL_* named in docs with zero non-test reads in src/ (unshipped or removed).
    • [4] Known stale patterns — recurring renames (tests/integration/flows/…/application/flows/, the signals/contract/ sibling rename, runtime/mount.tsx, InkPromptAdapter, PromptPort).
    • [5] Symbol sample — backticked identifiers to spot-check; too noisy to auto-resolve, so pick the load-bearing ones and grep them yourself.

Read the full file on GitHub · 95 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 95 lines · 181 tokens per session scan A ac860cf3f165

Subscribe to this mod's changes

drift-sweep is a skill published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed yesterday), licensed MIT. It adds 181 tokens to every session and 1,571 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

atomic-debug

Hypothesis-driven debugging skill. Use when a bug, test failure, crash, or unexpected behavior is reported. Auto-trigger on error pastes or "broken/doesn't work/failing" language. Explicit invocation: /atomic-debug. Output: symptom statement → hypothesis table → cheapest test first → root cause. No symptom-patching.…

damusix/atomic-claude · 114 tokens

system-health

Suggest whether the machine needs a DISK or MEMORY cleanup — and catch the case where Heimdall ITSELF is the hog (runaway orphaned python from the presence keeper). Use when the machine is slow / swapping / laggy, disk or "System Data" is full, memory is exhausted, at the start of a long session, or when the user asks…

randomittin/heimdall · 102 tokens

ci-self-heal

A diagnostic guide for analysing failed continuous-integration checks. Continuous integration, or CI, automatically tests and builds code changes; this guide classifies failures and suggests fixes without editing the code.

rushengzhou/sid-code · 73 tokens

incident-rca

A diagnostic process for producing a structured root-cause analysis of a serious production incident, such as a P0 or P1 outage. It compares logs, measurements, request traces, code changes, and architecture decisions, and gives ranked explanations and actions.

rushengzhou/sid-code · 82 tokens

bug-fix

A structured bug-fixing workflow that takes a problem from reproduction and evidence-based cause finding through approval, implementation, testing, and cleanup.

rushengzhou/sid-code · 62 tokens

rca

Disciplined root-cause analysis for diagnosing why something is broken. Use whenever the user is debugging a bug, regression, incident, outage, flaky or intermittent behavior, a failing test, or asks "why is X happening" / "why did this break" / "whats causing this" — even if they never say the words "root cause." It…

FlorinI/Florians-Claude-Code-Kit · 174 tokens