everywan-dev

everywan-dev/claude-code-engineering

Plugin Claude Code

Engineering skills and review agents for Claude Code, built on one rule: a check that cannot fail is not a check.

everywan-dev/claude-code-engineering

Plugin Claude Code

Turn Claude Code into a team that has to prove it: 44 skills, 8 review agents, a validation router, and a knowledge layer where nothing is asserted without a check that could have failed.

everywan-dev/claude-code-engineering

Instructions file

Instructions for everywan-dev/claude-code-engineering, a project described as: Turn Claude Code into a team that has to prove it. 44 skills, 8 review agents, a validation router and a knowledge layer where nothing is claimed without a check that could have failed.

everywan-dev/claude-code-engineering

Agent

Reviews migrations, deletions and any change that touches data or monetary amounts. Mandatory at level 3.

everywan-dev/claude-code-engineering

Agent

Actively tries to break a change before it ships. Mandatory at level 3. Its goal is to find the failure, not to sign off.

everywan-dev/claude-code-engineering

Agent

Writes up what was done, symptom first. Use when closing any work that took real time to understand.

everywan-dev/claude-code-engineering

Agent

Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.

everywan-dev/claude-code-engineering

Agent

Reviews container, orchestrator, reverse proxy, shared storage and network changes. Use as the second, independent validation on infrastructure work.

everywan-dev/claude-code-engineering

Agent

Implements code and configuration changes. Use when something has to be written or modified, not when something has to be diagnosed. Never validates its own work.

everywan-dev/claude-code-engineering

Agent

Reviews exposure, secrets, authentication and permissions. Mandatory on every level 3 change that touches login, tokens, roles or the network.

everywan-dev/claude-code-engineering

Agent

Writes and runs tests, and judges whether a check proves anything. Use on all level 2 and level 3 work. It is the first of the validators.

everywan-dev/claude-code-engineering

Command

Decide how much validation a change needs, and which agents and model.

everywan-dev/claude-code-engineering

Hook

Runs when a session starts, executing restore-memory-symlink.sh via bash. From everywan-dev/claude-code-engineering.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Build a throwaway build-a-throwaway-prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Use when deciding whether a table, a file, or a service can be deleted because it looks unused. Measure real access, rename before deleting, and check the units of every counter.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Use before pulling someone else's code, skills, prompts or configuration into your project, and before publishing anything that contains them. Turns "it was on GitHub" into an obligation you can actually meet.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Use when deciding how much review a change needs, and of what kind. What the change touches decides the level — not how big it looks, not how confident you feel.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Use when something did not happen and nothing complained — no error, no alert, an empty log, a change with no effect. Teaches how to read absence as a symptom and where silence gets manufactured.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Use when a change is about to touch a running system. Backup, dry run, rollback and per-node verification, in that order.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

everywan-dev/claude-code-engineering

Skill Claude CodeCodex

Use when checking whether curated knowledge is still fresh, reading freshness verdicts, or investigating why a unit shows drifted or unknown. Triggers on requests like "check freshness", "run the probes", "is this knowledge still current", "why does kb-0002 say unknown", or "read the knowledge index".