goal-extend

goal-extend is a command for Claude Code from lokafinnsw/claude-code-goal-mode. It costs 16 tokens per session (446 once invoked), scanned A, original, MIT.

A command for increasing the limits of an active goal without creating a new plan.

In plain words
What is it for?
Adding tokens, time, or iterations to a goal that is still running or has been stopped by its budget.
Why use it?
It allows work to continue after the goal reaches its token, time, or iteration limit while keeping its history and current position.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the goal-mode plugin — 2 skills, 20 commands, 2 hooks shipped together

Good fit Adding tokens, time, or iterations to a goal that is still running or has been stopped by its budget.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add lokafinnsw/claude-code-goal-mode
Claude Code
/plugin install goal-mode

Made for: Claude Code.

Or install goal-mode, the plugin that ships this one along with the rest of its 2 skills, 20 commands, 2 hooks.

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 goal-extend

README.md
[![agentmods](https://agentmods.dev/badge/commands/lokafinnsw/claude-code-goal-mode/goal-extend/github.svg)](https://agentmods.dev/commands/lokafinnsw/claude-code-goal-mode/goal-extend)
Your own site
<a href="https://agentmods.dev/commands/lokafinnsw/claude-code-goal-mode/goal-extend"><img src="https://agentmods.dev/badge/commands/lokafinnsw/claude-code-goal-mode/goal-extend/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.

agentmods 80×15 button for goal-extend

Your own site · 80×15
<a href="https://agentmods.dev/commands/lokafinnsw/claude-code-goal-mode/goal-extend"><img src="https://agentmods.dev/badge/commands/lokafinnsw/claude-code-goal-mode/goal-extend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 446 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00446
Opus 5 $0.00008 $0.00223
Sonnet 5 $0.00003 $0.00089
Haiku 4.5 $0.00002 $0.00045

Measured 9d ago against content hash da51edda72a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

goal-extend 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 9d 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.

commands/goal-extend.md · 43 lines

What it actually says

Goal Extend

Bumps budget limits on the active goal. Use when the triple budget was hit before the goal completed and you want to continue rather than /goal-clear + re-plan from scratch (which would lose cursor, history, evidence, audits, and tree shape).

Delta mode (+ prefix) — adds to current max:

/goal-mode:goal-extend --tokens +50M --time +4h

Absolute mode (bare value) — replaces current max:

/goal-mode:goal-extend --tokens 150M

Multiple dimensions in one call:

/goal-mode:goal-extend --tokens +50M --iter +1000 --time +2h

Suffixes:

  • tokens: k=1000, m=1000000 (case-insensitive)
  • time: h=hours, m=minutes, d=days, s=seconds (case-insensitive)
  • iter: bare integer only

Lifecycle:

  • pursuing → just bumps max, no transition.
  • budget-limited → bumps max AND transitions back to pursuing. Stop-hook will then resume firing continuation prompts on the existing plan.
  • Any other lifecycle (paused/achieved/unmet/draft/approved/awaiting-manual-approval) → rejected with cannot extend budget from lifecycle=.... Use the dedicated recovery path for those states.

Validation: new max must be ≥ already-consumed used count (cannot bump down past consumed budget).

Run via Bash:

"${CLAUDE_PLUGIN_ROOT}/scripts/goal-extend.sh" <parsed-args>
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. 9d ago First seen · 43 lines · 16 tokens per session scan A da51edda72a2

Subscribe to this mod's changes

goal-extend is a command published in the GitHub repository lokafinnsw/claude-code-goal-mode (3 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 446 once invoked, about $0.0001 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.