next

next is a skill for Claude Code from Hainrixz/claude-db. It costs 80 tokens per session (600 once invoked), scanned A, original, MIT.

A read-only coach that turns database audit findings into one ordered list of what to fix first. It ranks issues by seriousness, likely effect on the audit score, and effort.

In plain words
What is it for?
It helps prioritize database repairs, especially failures with high severity or issues that are easier to fix automatically.
Why use it?
It removes the need to sort through many findings and decide manually which problem deserves attention first.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the claude-db plugin — 36 skills, 6 agents, 1 hook shipped together

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/hainrixz/claude-db/next
Any agent
npx skills add Hainrixz/claude-db --skill next
Clone the repo
git clone --depth 1 https://github.com/Hainrixz/claude-db

Made for: Claude Code.

Or install claude-db, the plugin that ships this one along with the rest of its 36 skills, 6 agents, 1 hook.

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 next

README.md
[![agentmods](https://agentmods.dev/badge/skills/hainrixz/claude-db/next.svg)](https://agentmods.dev/skills/hainrixz/claude-db/next)
Your own site
<a href="https://agentmods.dev/skills/hainrixz/claude-db/next"><img src="https://agentmods.dev/badge/skills/hainrixz/claude-db/next.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 600 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 5.1 $0.00080 $0.00600
Opus 5 $0.00040 $0.00300
Sonnet 5 $0.00016 $0.00120
Haiku 4.5 $0.00008 $0.00060

Measured 6d ago against content hash 764828718b61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

next 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.

skills/next/SKILL.md · 22 lines

What it actually says

/claude-db:next

The coach. Turns a pile of findings into one ranked, do-this-next list with a reason for each item. Read-only — it prioritizes, it never writes or migrates.

$ARGUMENTS = [findings.json] [flags]. Use the most recent audit's findings, or a findings JSON path. If no audit has run, say so and suggest /claude-db:audit <target>.

Ranking (in order)

  1. Capped severity-5 first. Any status:"fail" + severity:5 on a relied-on axis caps that score at band F. These come first regardless of anything else — fixing them is the only way to lift the cap. (needs_api and confidence:"speculative" never cap, so they never jump the queue this way.)
  2. Then by severity × axis-weight — the finding's severity times the weight its module carries in the relevant category/axis (from references/scoring-model.md / the active PROFILES profile in score.mjs). A high-severity finding in a heavily-weighted category (e.g. Indexación at w20, Integridad referencial at w16) outranks the same severity in a light one (Naming at w6).
  3. Then by fixability: auto > proposed > advisory — surface the changes the tool can safely make for you before the ones needing judgment or that it will never write.
  4. Then by least reproduction cost — break ties toward findings whose verification.reproduce is cheapest to confirm (Tier-0 static check before a Tier-1 query before anything needs_api).

Output

A numbered list. For each item: the finding (id + one-line title), which score/axis it moves and roughly how much (banded magnitude high|medium|low — never a fabricated %), its fixability class, and the next concrete action ("run /claude-db:fix --category keys" / "run /claude-db:migrate <file>" / "needs a live DB: set $DATABASE_URL and re-audit at Tier 1"). Honor --axis and --top N. Respond in the user's language (EN/ES).

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 First seen · 22 lines · 80 tokens per session scan A 764828718b61

Subscribe to this mod's changes

next is a skill published in the GitHub repository Hainrixz/claude-db (19 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 600 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

dynamodb

Use when modeling or operating a DynamoDB table: deriving partition/sort keys from access patterns, single-table vs table-per-entity, adding a GSI/LSI, on-demand vs provisioned capacity, or diagnosing hot-partition throttling. NOT relational schema/SQL/EXPLAIN (that is postgresdb), NOT aggregation-pipeline document…

ericrisco/rsc-harness · 82 tokens

malloy-lookml-review

Analyze LookML files as prior art for Malloy modeling. Used during Step 1 (DISCOVER) when .lkml files are present. Coordinates reference files that extract business logic, relationships, and curation decisions. Works with or without a database connection.

malloydata/publisher · 58 tokens

database-design-patterns

Database schema design patterns and optimization strategies for relational and NoSQL databases. Use when designing database schemas, optimizing query performance, or implementing data persistence layers at scale.

NickCrew/Claude-Cortex · 37 tokens

terrabase-db-changes

Use when making Postgres schema or migration changes (CREATE/ALTER/DROP TABLE, indexes, columns, constraints, backfills) IN A PROJECT THAT DECLARES A TERRABASE TARGET (a TERRABASEDATABASEURL in its .env). Routes the change through terrabase's MCP tools for a deterministic safety analysis plus a local-Qwen plan, and…

Terrabase-in/terrabase · 98 tokens

erd-studio

Schema rules for ERD Studio data model files — the .erd-studio/ directory uses a two-file system (YAML model definitions + JSON domain diagrams) with strict format rules you must read before editing. Use this skill whenever the task touches files in .erd-studio/ (domain JSON, logical-models YAML, or .sync-plan.json)…

liam-machine/erd-studio · 162 tokens

database-sql

Design database schemas, write efficient SQL queries, create migrations, and optimize database performance. Use when working with databases, writing queries, or designing data models.

asgarovf/locusai · 35 tokens