resolve-drift

resolve-drift is a skill for Claude Code from rjroy/vibe-garden. It costs 72 tokens per session (517 once invoked), scanned A, original, MIT.

A tool for checking whether project reference pages still agree with the current source code and tests. This mismatch is called semantic drift: the documentation remains understandable but no longer describes how the software works.

In plain words
What is it for?
Use it to audit indexed reference pages against linked code and tests, report drift, and reconcile pages when needed.
Why use it?
It helps find outdated or contradictory documentation before developers rely on it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the field-guide plugin — 7 skills shipped together

Good fit Use it to audit indexed reference pages against linked code and tests, report drift, and reconcile pages when needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rjroy/vibe-garden/resolve-drift
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add rjroy/vibe-garden --skill resolve-drift
Clone the repo
git clone --depth 1 https://github.com/rjroy/vibe-garden

Made for: Claude Code.

Or install field-guide, the plugin that ships this one along with the rest of its 7 skills.

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 resolve-drift

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjroy/vibe-garden/resolve-drift/github.svg)](https://agentmods.dev/skills/rjroy/vibe-garden/resolve-drift)
Your own site
<a href="https://agentmods.dev/skills/rjroy/vibe-garden/resolve-drift"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/resolve-drift/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for resolve-drift

Your own site · 80×15
<a href="https://agentmods.dev/skills/rjroy/vibe-garden/resolve-drift"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/resolve-drift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 517 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.
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 $0.00072 $0.00517
Opus 5 $0.00036 $0.00259
Sonnet 5 $0.00014 $0.00103
Haiku 4.5 $0.00007 $0.00052

Measured 10d ago against content hash 46f7455634dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

resolve-drift 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 10d ago.

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.

field-guide/skills/resolve-drift/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve Drift

Compare reference prose against living implementation evidence and reconcile drift.

This is the semantic pass. It is intentionally more expensive than lint.

Inputs

Read indexed pages from .lore/reference/index.md or .lore/reference/index.html.

For each page, read evidence metadata:

  • Markdown: fg-evidence frontmatter
  • HTML: fg-evidence-code, fg-evidence-tests, and fg-evidence-symbols meta tags

If evidence is missing, either:

  • run update-evidence first, or
  • audit manually and report that the page needs evidence

Audit Method

For each page:

  1. Extract concrete claims from the prose.
  2. Read the listed code and test evidence.
  3. Search nearby code with rg when the evidence is incomplete.
  4. Decide whether each claim is:
    • current
    • stale prose
    • stale evidence
    • implementation drift from intended design
    • unverifiable policy or philosophy

Only flag contradictions when the code/tests and page make incompatible claims about the same subject. Do not treat different levels of detail as drift.

Parallel Review

For large wikis, split indexed pages into independent batches and use sub-agents when the user has allowed agent delegation. Each batch should return findings in this format:

Page:
Claim:
Evidence:
Verdict:
Suggested resolution:

Do not duplicate page batches across agents.

Fixing Drift

Prefer the smallest correction that restores truth:

  • update stale reference prose when code/tests are clearly current
  • update fg-evidence when the prose is true but anchors are incomplete
  • report a code/test issue when the page documents intended design and implementation contradicts it
  • mark historical pages as non-current when they are no longer meant to describe live behavior

Do not delete useful rationale just because implementation changed. Reframe it as history or a superseded decision when it still explains why the system evolved.

Output

Report grouped results:

  • fixed drift
  • remaining drift needing user decision
  • evidence gaps
  • pages audited with no actionable drift

Read the full file on GitHub · 77 lines

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. 10d ago First seen · 77 lines · 72 tokens per session scan A 46f7455634dd

Subscribe to this mod's changes

resolve-drift is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 517 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

procoder

Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…

azrtydxb/procoder · 101 tokens

code-review

The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…

jjanczur/tyran · 80 tokens

deslop

The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.

jjanczur/tyran · 58 tokens

goal-plan-clean

A guide for creating a reusable plan-review loop. It repeatedly checks a plan, fixes blocking issues and suggestions, and stops after approval or a small number of review rounds.

restarter/lets-workflow · 125 tokens

loop-test

A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.

restarter/lets-workflow · 112 tokens

take-task

A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.

restarter/lets-workflow · 76 tokens