claude

tce

Context-engineering workflow: ticket → intent → research → plan → implement, plus review/discuss/design commands and research agents. Agrees intents (/tce:intent) and works with any ticket system (tmt, GitHub, Jira, Linear, …).

1 on GitHubby Tobias Schlittv1.8.0updated 8 days ago
/

Plugin tce from marketplace toby-plugins in tobyS/toby-plugins. Commands read from the repo's manifest — 8 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Slash commands (14)

  • /tce:commit

    Commit the current session's changes with pre-commit checks (tests/typecheck/lint from the project profile) and a commit message in the project's configured convention.

  • /tce:design_explore

    Explore visual design solutions as mockups in the app's design language, iterate, and document the chosen direction. Optional, before implementing non-trivial UX changes.

  • /tce:discuss

    Act as a senior-engineer sparring partner to explore a technical challenge and document trade-offs. Discussion only — writes no code.

  • /tce:implement

    Implement an approved plan for a ticket or a ticketless intent — one fresh agent per phase, then verification with the bounded fix loop and the plan-compliance gate, the dossier and the closeout. Never delivers. Step 4 of the tce workflow. Needs CLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1 and BASH_DEFAUL

  • /tce:init

    Set up the tce workflow in this project — analyze the repo, agree a profile and ticket system, and write .claude/tce/ config + scaffold thoughts/.

  • /tce:intent

    Agree with the agent what a ticket (or ticketless input) means in this codebase — scope, outcome, anchors, criteria, decisions — and write it as an intent in thoughts/shared/intents/. Never modifies the ticket.

  • /tce:list

    List tickets as a table with their tce workflow stage — intent, research document, plan document, and implementation progress.

  • /tce:plan

    Plan a ticket with an intent, or a ticketless intent, from its research in a fresh agent — questions first, then a challenged plan and a brief for your approval. Step 3 of the tce workflow. Needs CLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1 and BASH_DEFAULT_TIMEOUT_MS=600000.

  • /tce:quickfix

    Run a small fix from your description to a verified change — an autonomously written ticketless intent, then research, plan, implementation, verification and the dossier in fresh agents, without plan approval. No ticket. Needs CLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1 and BASH_DEFAULT_TIMEOUT_MS=600000

  • /tce:refresh

    Re-analyze the project and reconcile .claude/tce/profile.md with it — proposes per-section changes, writes only what you approve.

  • /tce:research

    Research the codebase (and web) for a ticket with an intent, or a ticketless intent, in a fresh agent, and write the research document. Step 2 of the tce workflow. Needs CLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1 and BASH_DEFAULT_TIMEOUT_MS=600000.

  • /tce:review

    Pragmatic, in-depth code review of a ticket implementation or a custom scope; writes a review doc to thoughts/shared/reviews/.

  • /tce:ticket

    Create a ticket in the project's ticket system from your own text, after one confirmation. To agree with the agent what to build, use /tce:intent.

  • /tce:work

    Orchestrate a ticket with an intent, or a ticketless intent, from research to a verified, delivered change — one fresh agent per step, questions only during planning. Needs CLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1 and BASH_DEFAULT_TIMEOUT_MS=600000.

Subagents (13)

  • codebase-analyzer

    Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)

  • codebase-locator

    Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

  • codebase-pattern-finder

    codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like codebase-locator, but it will not only tell you the locatio

  • implementer

    Internal to tce's step commands (`/tce:work`, `/tce:implement`, `/tce:quickfix`) — not for direct use. The implementation step of the tce workflow: implements exactly one phase of an approved tce plan — changes, the phase's Automated checks with a bounded fix loop, the plan's implementation log and

  • plan-challenger

    Internal to tce's step commands (`/tce:work`, `/tce:plan`, `/tce:quickfix`) — not for direct use. Checks a freshly written plan against a closed checklist (criteria verifiable, tests per phase, no contradiction with stack or research, intent criteria covered, phases independently verifiable) and, in

  • plan-compliance-checker

    Verifies an implementation against a fixed list of acceptance/success criteria, from a fresh context. Call it at the end of implementation to get one verdict per criterion (met / not met / cannot verify from diff / needs human verification) against the diff — nothing else. Pass it only the criteria

  • planner

    Internal to tce's step commands (`/tce:work`, `/tce:plan`, `/tce:quickfix`) — not for direct use. The planning step of the tce workflow: plans a ticket or a ticketless intent from the intent and its research, questions first — returns the open questions before writing anything, then writes and commi

  • presenter

    Internal to tce's step commands (`/tce:work`, `/tce:plan`, `/tce:implement`, `/tce:quickfix`) and `/tce:intent` — not for direct use. Writes the human-facing summary of one finished tce artifact — a plan brief or its push-back delta, an intent, a dossier — from a fresh read-only context, shaped by t

  • researcher

    Internal to tce's step commands (`/tce:work`, `/tce:research`, `/tce:quickfix`) — not for direct use. The research step of the tce workflow: researches a ticket or a ticketless intent against the live codebase (fanning out to the locator, analyzer, pattern-finder, thoughts and web agents) and writes

  • thoughts-analyzer

    The research equivalent of codebase-analyzer. Use this subagent_type when wanting to deep dive on a research topic. Not commonly needed otherwise.

  • thoughts-locator

    Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name

  • verifier

    Internal to tce's step commands (`/tce:work`, `/tce:implement`, `/tce:quickfix`) — not for direct use. The verification step of the tce workflow: verifies a fully implemented tce plan — runs every test suite, runs the plan-compliance gate, then attempts every item the gate could not settle with the

  • web-search-researcher

    Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagent_type today to find any and all answers to your questions! It will research deeply to figure

Hooks (1)

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/scripts/check-init.sh

View source on GitHub

More from tobyS/toby-plugins

All 4 plugins →

tsf

claude

Toby Software Factory: an agentic software factory over a GitHub-issue backlog — one work step per cycle in a fresh context, async human gates on the issue, artifacts in the repo, and approved work landed unattended.

3 commands · 12 agents

1

tle

claude

Toby Loop Engineering: an autonomous convergence loop — define a machine-checkable goal, then iterate verify → spec → implement until every checklist item verifiably passes. Greenfield-first; file-only handoffs under thoughts/shared/loops/.

2 commands · 4 agents

1

tmt

claude

Toby Markdown Tickets: lightweight Git-tracked ticket tracker — tickets as markdown files in your repo, owning the envelope (sequential numbering, status-lifecycle hooks, create/update). tce's native ticket backend.

4 commands · hooks

1

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

Long-term semantic memory for Claude Code, powered by OpenViking

5 skills · 1 command · 1 MCP server · hooks

volcengine/OpenViking 42,126

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

PRD generation and conversion skills for the Ralph autonomous agent loop

2 skills

snarktank/ralph 22,224

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

Maintain tce?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins4 plugins