mtk-agent-toolkit: Skill for Claude Code

.claude/skills/spec-drift-detection/SKILL.md

spec-drift-detection is a skill for Claude Code from moberghr/mtk-agent-toolkit. It costs 39 tokens per session (3,079 once invoked), scanned A, original, MIT.

A check performed after coding to compare the actual changes with an approved specification. A specification is the agreed description of what the change should include.

In plain words
What is it for?
Use it after implementation and before review when a specification manifest exists, particularly for controlled or compliance-sensitive changes.
Why use it?
It catches changes that add unapproved work, miss promised work, touch unexpected files, or alter security and public interfaces beyond the agreed scope.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions Codex.

This is moberghr/mtk-agent-toolkit's own configuration. It tells Claude Code how to work on mtk-agent-toolkit 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 mtk-agent-toolkit configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/monorepo-ripple.sh $(git diff --name-only HEAD).

Part of the mtk plugin — 45 skills, 6 agents, 7 hooks, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. 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/moberghr/mtk-agent-toolkit/main/.claude/skills/spec-drift-detection/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code.

Or install mtk, the plugin that ships this one along with the rest of its 45 skills, 6 agents, 7 hooks, 1 MCP server.

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 spec-drift-detection

README.md
[![agentmods](https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/spec-drift-detection/github.svg)](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/spec-drift-detection)
Your own site
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/spec-drift-detection"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/spec-drift-detection/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 spec-drift-detection

Your own site · 80×15
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/spec-drift-detection"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/spec-drift-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,079 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 202
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00039 $0.03079
Opus 5 $0.00019 $0.01540
Sonnet 5 $0.00008 $0.00616
Haiku 4.5 $0.00004 $0.00308

Measured 8d ago against content hash 8f751afb3118, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spec-drift-detection 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 8d 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.

.claude/skills/spec-drift-detection/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Drift Detection

Overview

Verify that the implementation actually delivered what the spec promised — nothing more, nothing less. Drift between spec and implementation is a compliance risk in regulated environments: it means the approval gate at Phase 2.5 did not cover the final code. Detect divergence before review.

When To Use

  • After implementation batches complete
  • Before handing to compliance-reviewer in Phase 4
  • When a spec manifest exists at docs/specs/<date>-<slug>.json
  • Whenever a change was supposed to follow a spec-driven flow and the reviewer wants to confirm the scope was honored

When NOT To Use

  • Quick fixes that ran through the fix workflow without a spec
  • Typo fixes and config updates
  • Sessions where no spec manifest was ever produced

Workflow

  1. Locate the spec manifest.

    • Default: the latest docs/specs/*.json on the current branch.
    • Override: accept an explicit path if the engineer supplies one.
    • If no manifest exists, STOP and report BLOCKED — no spec manifest found; drift cannot be checked. Either generate one via spec-driven-development or confirm this change is quick-fix scope.
  2. Load the manifest schema fields:

    • scope — classification string
    • change_manifest — array of { path, action, purpose }
    • public_contracts — array of { kind, signature, change }
    • success_criteria — array of { id, description, verification }
    • out_of_scope — array of strings
    • security_impact — enum string
  3. Collect actual change data:

    • Preferred (deterministic): run bash scripts/validate-handoff.sh docs/specs/<date>-<slug>.json to compute file-level and security-impact drift against the manifest. Treat its output as authoritative for those axes.
    • If the handoff has an implement.actual_files array, diff it against change_manifest[].path directly — no git invocation needed.
    • Otherwise, fall back to git diff --name-status <base>...HEAD.
    • For contract-level drift (not covered by the script): grep the diff for added/modified public contracts (controller routes, handler classes, exported functions, etc., per active tech stack).

Read the full file on GitHub · 241 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. 8d ago First seen · 241 lines · 39 tokens per session scan A 8f751afb3118

Subscribe to this mod's changes

spec-drift-detection is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 3,079 once invoked, about $0.0002 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.