A command for creating a new ContextFun workstream and its first session, then printing a Markdown summary pack. A workstream is a named line of work stored with local chat transcripts.

Use it to start a workstream, optionally import the current chat, and create a unique name automatically if the requested name already exists.

It gives a new task its own place to preserve context and can optionally include the currently visible chat in the first session.

ctx start — Skill for Claude Code and Codex by dchu917/ctx

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.

Any agent

npx skills add dchu917/ctx --skill ctx-start

Clone the repo

git clone --depth 1 https://github.com/dchu917/ctx

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dchu917/ctx/ctx-start/github.svg)](https://agentmods.dev/skills/dchu917/ctx/ctx-start)

Your own site

<a href="https://agentmods.dev/skills/dchu917/ctx/ctx-start"><img src="https://agentmods.dev/badge/skills/dchu917/ctx/ctx-start/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dchu917/ctx/ctx-start"><img src="https://agentmods.dev/badge/skills/dchu917/ctx/ctx-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 213 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.00213
Opus 5.5	$0.00008	$0.00085
Sonnet 5.5	$0.00004	$0.00043
Haiku 4.5	$0.00002	$0.00021

Measured 2mo ago against content hash cd9b18537ef5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ctx start 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/ctx_start.sh, scripts/skills/ctx_start.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/claude/ctx-start/SKILL.md · 21 lines

What it actually says

Usage

In chat:
- /ctx start <workstream> — creates a new workstream and its first session, then prints the pack
- /ctx start --pull <workstream> — also ingests the current visible chat into that first session
- --pull can appear before or after the workstream name

What it runs

bash ./scripts/ctx_start.sh
Falls back to ctx start or python3 scripts/ctx_cmd.py start

Notes

If the requested workstream name already exists, ctx automatically creates name (1), name (2), and so on.
Use /ctx resume <workstream> to continue an existing workstream.
Uses local transcript storage (default ~/.claude/projects, ~/.codex/sessions).
Initialize ContextFun with scripts/quickstart.sh.

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 21 lines · 21 tokens per session scan A cd9b18537ef5

Subscribe to this mod's changes

ctx start is a skill published in the GitHub repository dchu917/ctx (127 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 213 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Project management cli codex context-management developer-tools sqlite

ctx start next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ctx startdchu917/ctx	Skill	127	6mo ago	MIT	A	21	Claude Code, Codex
codemarkDanielCardonaRojas/codemark	Skill	138	today	MIT	A	97	Claude Code
kn-flowknowns-dev/knowns	Skill	251	1mo ago	MIT	A	38	Claude Code, Codex
kn-implementknowns-dev/knowns	Skill	251	1mo ago	MIT	A	20	Claude Code
kn-specknowns-dev/knowns	Skill	251	1mo ago	MIT	A	17	Claude Code
brainctlTSchonleber/brainctl	Skill	78	10d ago	MIT	A	45	Claude Code, Codex
kn-handoffknowns-dev/knowns	Skill	251	1mo ago	MIT	A	37	Claude Code, Codex