drift-canary

drift-canary is a skill for Claude Code, Codex from HetCreep/CoalMine. It costs 78 tokens per session (1,979 once invoked), scanned A, original, Apache-2.0.

A code review for changes that might make a database, API, or shared data format incompatible with existing software.

In plain words
What is it for?
Use it when changing database tables, API endpoints or fields, serialized data such as JSON, shared libraries, or required configuration.
Why use it?
It helps catch changes that could crash deployments or stop older clients and services from working.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Part of the coalmine plugin — 9 skills shipped together

Good fit Use it when changing database tables, API endpoints or fields, serialized data such as JSON, shared libraries, or required configuration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hetcreep/coalmine/drift-canary
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 HetCreep/CoalMine --skill drift-canary
Clone the repo
git clone --depth 1 https://github.com/HetCreep/CoalMine

Made for: Claude Code, Codex.

Or install coalmine, the plugin that ships this one along with the rest of its 9 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 drift-canary

README.md
[![agentmods](https://agentmods.dev/badge/skills/hetcreep/coalmine/drift-canary/github.svg)](https://agentmods.dev/skills/hetcreep/coalmine/drift-canary)
Your own site
<a href="https://agentmods.dev/skills/hetcreep/coalmine/drift-canary"><img src="https://agentmods.dev/badge/skills/hetcreep/coalmine/drift-canary/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 drift-canary

Your own site · 80×15
<a href="https://agentmods.dev/skills/hetcreep/coalmine/drift-canary"><img src="https://agentmods.dev/badge/skills/hetcreep/coalmine/drift-canary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,979 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 $0.00078 $0.01979
Opus 5 $0.00039 $0.00989
Sonnet 5 $0.00016 $0.00396
Haiku 4.5 $0.00008 $0.00198

Measured 6d ago against content hash d64da19b5542, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

drift-canary 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 6d 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.

plugin/skills/drift-canary/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Canary (Contract & Schema Drift Audit)

Language: Generate EVERYTHING at runtime in the user's language — questions, answer options, menu labels, recommendations, report narrative. Detect from their messages; never default to English just because this file is English. English is allowed only for technical terms: commands, paths, code identifiers, severity labels (CRITICAL/HIGH/MEDIUM/LOW), and tier names (Light/Standard/Heavy).

Config reads — every config key, always the CASCADE, never the bare project file: ~/.claude/.coalmine.json first, then the project config (own agent dir → other known agent dirs → legacy <gitroot>/.coalmine.json), project wins per key. A bare project read is ABSENT on a machine configured only globally, so it silently yields defaults.

Audit code to ensure changes do not break backward compatibility or cause database/API mismatches.

Auditing Categories

  1. Breaking Schema Migrations — dropping columns, changing types, or adding non-null columns without defaults (crashes on deploy).
  2. API Contract breaking changes — modifying existing REST/GraphQL properties, removing endpoints, or adding required query fields that break old clients.
  3. Serialization mismatches — editing properties in serialized payloads (JSON, Protobuf, XML) without deserialization fallbacks.
  4. Library Contract Drift — changing a public method signature in a shared library without a deprecated wrapper.
  5. Environment Configuration drift — introducing new required config keys (.env / OS vars) without defaults or fallback.

Expand/contract migration rules, per-format serialization fallbacks, and the breaking-vs-additive API checklist: read references/checks.md before scanning.

Scope: honor .coalmine.json schemaPaths / migrationDirs if set — scan those globs/dirs; else infer by inspecting the repo.

Discipline

  • Style Drift Resolution (Fix mode): when an approved fix touches mixed-style code, conform the minority patterns to the dominant style (highest average usage) to minimize churn — never start a standalone style refactor.

Read the full file on GitHub · 83 lines

Files

What ships with it

3 files 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. 6d ago Changed · +2 lines d64da19b5542
  2. 10d ago First seen · 81 lines · 78 tokens per session scan A ae902ff33741

Subscribe to this mod's changes

drift-canary is a skill published in the GitHub repository HetCreep/CoalMine (12 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 1,979 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 2026-08-30.

Related

Other skills, from other repositories

performance-audit

Full-stack performance health check across 12 dimensions. Rendering, bundles, assets, API/network, algorithms, memory, database, caching, Web Vitals, backend runtime, concurrency, and framework-specific pathologies. Evidence-based Impact Models with confidence tiers and a prioritized optimization roadmap. Switches…

greglas75/zuvo · 90 tokens

django-patterns

Django + Django REST Framework implementation discipline — project layout, model design, DRF serializers/viewsets, service layer, caching, signals, middleware, query performance, AND the full Django security surface (SECURE settings, authentication, authorization, SQL-injection and XSS prevention, CSRF, file-upload…

Nmor/the-claude-council · 108 tokens

backend-patterns

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Nmor/the-claude-council · 31 tokens

dynamodb-patterns

DynamoDB single-table design, composite keys, GSI design, conditional writes, BatchWrite/BatchGet chunking, atomic counters, TTL, streams, and cross-tenant isolation patterns. Auto-fires for files importing from @aws-sdk/lib-dynamodb or @aws-sdk/client-dynamodb.

Nmor/the-claude-council · 68 tokens

jpa-patterns

JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.

Nmor/the-claude-council · 33 tokens

supabase

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies…

supabase/agent-skills · 185 tokens