start-thread

A command for opening or resuming a tracked unit of work, such as a feature, bug, research task, refactor, or experiment. It creates a STATE handoff document for new work or briefs the agent from an existing one.

In plain words
What is it for?
Use it to create a new work thread, resume an existing thread, normalize its name, and inspect the relevant project and Git context.
Why use it?
It gives each piece of work a persistent place to record decisions and progress, making it easier to continue after context loss.

Skill for Claude CodeCodex

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/shck-dev/ccx-context-system/start-thread
Any agent
npx skills add shck-dev/ccx-context-system --skill start-thread
Clone the repo
git clone --depth 1 https://github.com/shck-dev/ccx-context-system

Made for: Claude Code, Codex.

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,409 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 $0.00130 $0.01409
Opus 5 $0.00065 $0.00705
Sonnet 5 $0.00026 $0.00282
Haiku 4.5 $0.00013 $0.00141

Measured yesterday against content hash 83e5ed1e0f88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start-thread 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 yesterday.

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.

plugins/ccx/skills/start-thread/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start or resume a thread — scratch workspace with a handoff doc

Topic requested: $ARGUMENTS

Project + config: !bun "${CLAUDE_PLUGIN_ROOT}/scripts/where.ts"

Current branch: !git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "(not a git repo)"

Existing threads: !bun "${CLAUDE_PLUGIN_ROOT}/scripts/threads.ts" --slugs

Do this

  1. If $ARGUMENTS is empty, ask for the topic — don't guess.
  2. Normalize the topic to a slug — run via Bash: bun "${CLAUDE_PLUGIN_ROOT}/scripts/slug.ts" "<topic>" (one shared identity function — never re-implement slugging by hand; if the variable shows as a literal, use the plugin root: path from the injected block above). With ticket_system: none a thread is any unit of work; ticket-system adapters may extend this later.
  3. If <scratch_root>/<slug>/ already has a STATE doc → RESUME. This is the normal day-2 path, not an error: no questions, no "want me to open it?" menu — brief and get to work. Treat slugs as the SAME thread when they match ignoring case and separators (CP-1758cp-1758cp1758 — the normalizeForMatch rule in scripts/lib/identity.ts): a near-match in the existing-threads list above resumes THAT thread. Never overwrite or re-scaffold an existing STATE (skip steps 4–6 entirely). Do all of this:
    1. Read the whole STATE doc — Status, the ask, plan, current state, open/deferred.
    2. Pull live deltas (parallel; each optional-degrade — an unreachable source gets a one-line note, never stalls the resume): current branch; a git worktree list / git branch --list match on the slug; if a matching worktree/branch exists — git status --porcelain (dirty files) and gh pr list --head <branch> --state all --json number,state,reviewDecision --limit 1 (when gh resolves).
    3. Report a resume briefing — where the user left off (Status, next plan step, open items), then what changed since (branch moved / PR merged / dirty files). Explicitly flag any live fact that CONTRADICTS the STATE. End ready to work — not with a menu.
    4. Resume is read-only on the STATE doc — flag drift in the briefing; the session updates STATE as work actually proceeds (the state-freshness-guard Stop hook enforces this before the session ends).
  4. Seed the ask from the conversation — there is no ticket system to pull from. If the goal isn't clear from context, ask for one line. Mark anything unknown as TODO rather than inventing.
  5. Create <scratch_root>/<slug>/ and write the STATE doc from the template below, filling the frontmatter (title: <slug> · kind: thread · summary: one-line blurb) and The ask. Use the state_basename from the injected config block (default STATE.md).
  6. Version-control check: if this is a git repo and <scratch_root> is not ignored (git check-ignore -q <scratch_root> fails), ASK whether to add it to .gitignore — some people want the notebook versioned, some never want notes in PRs. Don't silently do either.
  7. Report the path created and a one-line summary. (No need to run /ccx:save-state for indexing — the auto-compile-index hook recompiles the INDEX on every STATE write.)

Read the full file on GitHub · 101 lines

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. yesterday First seen · 101 lines · 130 tokens per session scan A 83e5ed1e0f88

Subscribe to this mod's changes

start-thread is a skill published in the GitHub repository shck-dev/ccx-context-system (1 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 1,409 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

orchestrator

FULLY AUTONOMOUS Flutter development pipeline orchestrator. Smart routing: PM analyzes -> creates targeted tasks -> Orchestrator executes only needed agents. Supports Asana task URLs. Includes QE verification via Maestro E2E tests. 7-phase flow: PM -> TodoWrite -> Execute -> Review -> Tests -> QE E2E -> Close.

aleksandr-chaika/flutter-clean-arch-skills · 72 tokens

flutter-guide

Flutter/BLoC Clean Architecture patterns, review checklists, and testing guides. Background knowledge for flutter-dev, flutter-reviewer, flutter-tester. Not user-invocable.

aleksandr-chaika/flutter-clean-arch-skills · 39 tokens

maestro-flutter

Maestro E2E testing knowledge for Flutter apps. YAML-based flows, TestKeys, visual regression, Maestro MCP integration. Background knowledge for QE E2E testing phase.

aleksandr-chaika/flutter-clean-arch-skills · 41 tokens

android-kotlin-compose

Android development with Kotlin and Jetpack Compose. Use when user mentions "Compose", "Jetpack Compose", "Material3", "Hilt", "Room", "ViewModel", or needs to build Android UI, implement MVVM architecture, manage Compose state, or integrate Jetpack libraries (Navigation, Room, Hilt, ViewModel). Triggers on…

and3r817/dot-claude-plugins · 84 tokens

android-kotlin-coroutines

Android development with Kotlin Coroutines and Flow. Use when user mentions "coroutines", "suspend", "Flow", "StateFlow", "SharedFlow", "viewModelScope", "lifecycleScope", or needs to implement async programming, handle structured concurrency, integrate coroutines with Retrofit/Room/WorkManager, or write coroutine…

and3r817/dot-claude-plugins · 87 tokens

codex-advisor

Advisory consultation skill for architectural reviews, design decisions, code analysis, and technology evaluation. Codex provides recommendations without making code changes. Invoked by phrases like "consult Codex", "get Codex's opinion", "ask Codex about", "have Codex review", "Codex analysis", "validate this…

and3r817/dot-claude-plugins · 85 tokens