specrew-drift-check

specrew-drift-check is a skill for Claude Code, Codex from alonf/specrew. It costs 29 tokens per session (1,166 once invoked), scanned A, original, MIT.

A specification-drift checker that compares completed work with the requirement it was meant to satisfy.

In plain words
What is it for?
Use it after a task or during review to assess a task output, record findings in a drift log, and provide evidence for a review decision.
Why use it?
It reveals when the implementation, plan, tasks, or delivered result no longer match the source specification.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/alonf/specrew/specrew-drift-check
Any agent
npx skills add alonf/specrew --skill specrew-drift-check
Clone the repo
git clone --depth 1 https://github.com/alonf/specrew

Made for: Claude Code, Codex.

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 specrew-drift-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/alonf/specrew/specrew-drift-check.svg)](https://agentmods.dev/skills/alonf/specrew/specrew-drift-check)
Your own site
<a href="https://agentmods.dev/skills/alonf/specrew/specrew-drift-check"><img src="https://agentmods.dev/badge/skills/alonf/specrew/specrew-drift-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,166 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.01166
Opus 5 $0.00015 $0.00583
Sonnet 5 $0.00006 $0.00233
Haiku 4.5 $0.00003 $0.00117

Measured 5d ago against content hash 0611d8f262a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specrew-drift-check 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 5d 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.

.agents/skills/specrew-drift-check/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

specrew-drift-check

Type: Analysis Skill
Schema: v1
Status: Active execution/review method

Purpose

Detect specification drift by comparing delivered output against the cited requirement and return a review-ready drift decision with evidence.

When to Use

  • After each task completion
  • During Review/Demo as the batch fallback
  • Any time a reviewer or implementer suspects the output and the spec disagree

Inputs

Input Type Required Description
task_id string Yes Task identifier for the completed work (for example T-012)
task_output string/path Yes The deliverable or output from the completed task
requirement_ref string Yes Requirement identifier (for example FR-003)
requirement_text string Yes Full text of the requirement from the spec
spec_path path Yes Path to the authoritative spec file
drift_log_path path No Path to iterations/NNN/drift-log.md when the result should be prepared for immediate logging
reviewer_notes string/array No Existing reviewer concerns or context that should be tested against the requirement

Process

  1. Confirm the authority before judging the output:
    • locate requirement_ref in spec_path
    • use the spec text as authoritative if requirement_text was copied inaccurately
    • extract required behavior, explicit constraints, exclusions, and deferred scope
  2. Gather concrete evidence from task_output:
    • identify the files, commands, artifacts, or behavior that prove what was delivered
    • do not return PASS based on intention or a status note alone
  3. Compare the delivered output to three drift questions:
    • Did we omit something required?
    • Did we add something not authorized?
    • Did we contradict the requirement or a documented deferral?
  4. Classify each mismatch for reviewer clarity:
    • gold-plating = unauthorized added behavior
    • incomplete = required behavior missing or only partially delivered
    • violation = delivered behavior contradicts the requirement or accepted scope boundary
  5. Choose a resolution path for each drift event:
    • spec-updated
    • implementation-reverted
    • deferred
    • human-decision
  6. Produce a drift-log-ready result:
    • PASS: provide explicit evidence summary and say no drift event is required
    • DRIFT: emit contract-aligned event data and a Markdown snippet that can be copied into drift-log.md
    • if drift_log_path points at a zero-drift placeholder log, note that the summary text must be updated when the first event is added

Read the full file on GitHub · 104 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. 5d ago First seen · 104 lines · 29 tokens per session scan A 0611d8f262a2

Subscribe to this mod's changes

specrew-drift-check is a skill published in the GitHub repository alonf/specrew (54 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 1,166 once invoked, about $0.0001 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens