e1024kb

e1024kb/wise-claude

Plugin Claude Code

Home of the wise plugin — a Claude Code copilot with flat /wise- slash commands, a workflow engine, and autonomous git / PR / ticket-planning pipelines.

e1024kb/wise-claude

Instructions file CodexOpenCode

Instructions for e1024kb/wise-claude, covering agents.md, working in this repo, the wise sdlc agent roster and adding or editing a role.

e1024kb/wise-claude

Instructions file

Instructions for e1024kb/wise-claude, covering wise-claude, structure, editing model and conventions.

e1024kb/wise-claude

Plugin Claude Code

wise copilot — flat slash commands, a workflow engine with an SDLC agent roster (CEO/CTO/architect/engineer/QA/security/SRE/…), a session-mining self-improvement loop (mine + refine + reset), and shared scripts for everyday git / PR / ticket-planning / skill-authoring tasks. The /wise command is a natural-language he.

e1024kb/wise-claude

Agent

Use for system and component design — choosing patterns, defining boundaries and data flow, weighing trade-offs (scalability, consistency, cost, complexity), and recording decisions ADR-style. Pick this for any workflow step that must decide how something is built before it is built, or that produces a design doc /…

e1024kb/wise-claude

Agent

Use for the highest-altitude business calls — prioritizing across competing initiatives, framing a trade-off in terms of value, risk, cost, and timing, or making a go / no-go decision. A chief executive who sets direction and names what's out of scope. Pick this for any workflow step that needs a strategic verdict…

e1024kb/wise-claude

Agent

Use for reviewing a diff or branch — correctness bugs, security issues, and clear quality problems, severity-tagged, one finding per line, no praise, no scope creep. A staff-level reviewer who finds and explains but does not rewrite. Pick this for any workflow step that gates a change on review before it ships, not…

e1024kb/wise-claude

Agent

Use for technical strategy calls — build-vs-buy, platform and tech-stack direction, technical-risk assessment, and arbitrating cross-team architecture disputes. A chief technology officer who sets direction and delegates detailed design. Pick this for any workflow step that needs a binding technical decision with a…

e1024kb/wise-claude

Agent

Use for CI/CD, infrastructure-as-code, containerization, and deployment strategy — authoring or fixing pipelines, Dockerfiles, Terraform/Helm/k8s manifests, and choosing a safe rollout (blue-green, canary) with a rollback path. A senior DevOps engineer who verifies with a dry run or plan output before declaring done.…

e1024kb/wise-claude

Agent

Use to turn an approved plan or goal into a sequenced delivery plan — decomposing work into tasks with acceptance criteria, estimating effort, mapping dependencies into parallelizable waves, and flagging risks and blockers. Pick this for any workflow step that plans who-does-what-and-when before code is written. Does…

e1024kb/wise-claude

Agent

Use to turn a problem into crisp requirements — user stories, testable acceptance criteria, MVP-vs-later scope, and prioritization grounded in user and market reality. A senior PM who validates the problem before speccing the solution. Pick this for any workflow step that produces requirements or scope, not the…

e1024kb/wise-claude

Agent

Use for test strategy and quality — enumerating edge cases, designing a test plan, writing or extending automated tests and running them, and filing precise, reproducible defect reports. Pick this for any workflow step that decides what to test and how or that hardens a change with coverage, rather than building the…

e1024kb/wise-claude

Agent

Use for application-security review — threat-modelling a change, auditing code for vulnerabilities, or reviewing auth, crypto, secrets, and input-handling. A senior AppSec engineer who maps the attack surface, runs STRIDE against the diff, and rates every finding by severity with a concrete fix. Pick this for any…

e1024kb/wise-claude

Agent

Use for hands-on implementation — building a feature, fixing a bug, refactoring, or writing tests against an existing codebase. A senior, polyglot engineer who reuses what's there before writing new code and leaves the tree working. Pick this for any workflow step that turns a decided plan or a well-scoped task into…

e1024kb/wise-claude

Agent

Use for reliability, observability, and operability — defining SLIs/SLOs and error budgets, designing monitoring/alerting on the golden signals, capacity planning, and writing incident-response runbooks. A senior SRE who reasons about failure modes and turns them into measurable goals and actionable alerts. Pick this…

e1024kb/wise-claude

Agent

Use for developer-facing documentation — READMEs, API references, how-to guides, changelogs, and inline doc comments. A senior technical writer who reads the actual code so every claim is accurate, then writes structured, skimmable docs with runnable examples. Pick this for any workflow step that produces or updates…

e1024kb/wise-claude

Agent

Use for experience design — mapping a user flow, designing interaction and information architecture, auditing usability and accessibility (WCAG), or critiquing a proposed or existing UI. A senior UX/UI designer who delivers an experience spec, not production CSS. Pick this for any workflow step that asks "how should…

e1024kb/wise-claude

Hook

Runs when a session ends, executing session-end-ingest.sh via bash. From e1024kb/wise-claude.

e1024kb/wise-claude

Skill Claude CodeCodex

Code-comment rules for EVERY comment and docstring written on the user's behalf in ANY programming language. ALWAYS consult this skill before writing, rewriting, or reviewing a code comment, docstring, or inline annotation - whether adding comments to new code, editing code that carries comments, or when the user says…

e1024kb/wise-claude

Skill Claude CodeCodex

Autonomously code-review the current branch and apply the fixes — dispatches the 3-lens panel of parallel reviewer subagents (correctness, security, tests — reviewer effort set by the session token-budget profile) over origin/ ..HEAD, applies the concrete correctness / security / clear-quality findings (skipping…

e1024kb/wise-claude

Skill Claude CodeCodex

Draft one Conventional-Commits subject line from your pending git changes — both staged (git diff --cached) and unstaged-but-modified tracked files (git diff) — Jira-scoped (e.g. feat(PROJ-777): …) when a key is detectable from the branch, diff, recent commits, or the live session, and unscoped (e.g. feat: …)…

e1024kb/wise-claude

Skill Claude CodeCodex

Sweep every working-tree change into the index (git add -A — modifications, deletions, and new untracked files), draft a Conventional-Commits subject from the staged diff, run git commit, then git push to the tracked upstream. If the working tree is already clean but the local branch is ahead of upstream (e.g. a…

e1024kb/wise-claude

Skill Claude CodeCodex

Sweep every working-tree change into the index (git add -A — modifications, deletions, and new untracked files), draft a Conventional-Commits subject from the staged diff (Jira-scoped when a key is detectable from the branch / diff / log / session), and run git commit. Closes the loop that /wise-commit-message opens …

e1024kb/wise-claude

Skill Claude CodeCodex

Story-point estimation reference — a Fibonacci 0.5 → 13 SP scale for sizing work across frontend, backend, mobile, and all teams, including how to size uncertain work and the "anything > 8 SP is a research ticket, not an implementation ticket" rule. Use whenever the user says "estimate", "story points", "SP", "size…