wise-fork

wise-fork is a skill for Claude Code, Codex from e1024kb/wise-claude. It costs 138 tokens per session (1,146 once invoked), scanned A, original, MIT.

A session-control skill for starting fresh work after a conversation is forked. A fork is a separate copy of a coding session that can continue in parallel with the original.

In plain words
What is it for?
Use it after forking to discard inherited in-progress tasks and begin a new goal, while keeping earlier information only as background context.
Why use it?
It prevents the new session from repeating unfinished work or changing files based on tasks that still belong to the original session.

Skill for Claude CodeCodex

Part of the wise plugin — 32 skills, 22 agents, 1 hook shipped together

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/e1024kb/wise-claude/wise-fork
Any agent
npx skills add e1024kb/wise-claude --skill wise-fork
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude

Made for: Claude Code, Codex.

Or install wise, the plugin that ships this one along with the rest of its 32 skills, 22 agents, 1 hook.

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.

agentmods badge for wise-fork

README.md
[![agentmods](https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-fork.svg)](https://agentmods.dev/skills/e1024kb/wise-claude/wise-fork)
Your own site
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-fork"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-fork.svg" alt="Measured on agentmods" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,146 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 $0.00138 $0.01146
Opus 5 $0.00069 $0.00573
Sonnet 5 $0.00028 $0.00229
Haiku 4.5 $0.00014 $0.00115

Measured 4d ago against content hash 67f73bee9509, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wise-fork 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 4d ago.

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/wise/skills/wise-fork/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wise-fork - reorient a forked session

Why this skill exists

Forking a session copies the whole conversation into a new, parallel session. The copy inherits every open thread: half-finished tasks, promised next steps, an in-progress plan. Left alone, the agent in the fork will try to finish them - duplicating work the original session is still doing, and possibly fighting it over the same working tree. This skill draws a hard line: context before the fork is background, work before the fork is not yours.

Invocation

/wise-fork
/wise-fork <new goal in free prose>
/wise:wise-fork [<new goal>]   # canonical namespaced form

Arguments

Read $ARGUMENTS. Everything (if anything) is free-form text: the first task of this forked session. No flags, no validation - prose is prose. When empty, acknowledge the fork and wait for the user's next message.

Procedure

1. Adopt the fork contract

From this point on, apply these rules to the entire conversation above this invocation:

  • Context is background, not a backlog. Facts, decisions, codebase knowledge, and user preferences learned before the fork stay valid - use them freely as reference.
  • In-flight work belongs to the original session. Do not continue, resume, retry, re-verify, or "quickly finish" any task, plan, todo, or promise made before the fork - even ones that look one step from done. The original session runs in parallel and owns them; doing them here duplicates work and creates conflicts.
  • Pending questions and offers are void. An unanswered question or an offer you made before the fork ("say the word and I'll ...") is not carried over. Do not act on it and do not re-ask it.
  • Distrust remembered file state. The original session may be modifying the same working tree in parallel. Anything you recall about file contents, branch position, or uncommitted changes may already be stale - re-check before relying on it or editing.

2. Ground the starting state (git repos only)

Read the full file on GitHub · 115 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. 4d ago First seen · 115 lines · 138 tokens per session scan A 67f73bee9509

Subscribe to this mod's changes

wise-fork is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 9d ago), licensed MIT. It adds 138 tokens to every session and 1,146 once invoked, about $0.0007 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

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens

codex-test-gen

Generate unit tests for specified functions using Codex MCP.

sd0xdev/sd0x-harness · 15 tokens

ensure-pipelines-host

Ensures the tenant has a usable Power Platform Pipelines host environment before any pipeline operation runs. Detects host state via the same resolution order as the Power Apps UI (org-db setting → BAP env metadata → default-custom-host setting); if any existing host (Platform or Custom) is found, uses it. If no host…

microsoft/power-platform-skills · 222 tokens