help

A command that explains Goalkeeper, a guard for Claude Code and Codex that keeps an unfinished checklist active when the agent tries to stop.

In plain words
What is it for?
It documents commands for starting goals, adding verifiable goals, viewing status, changing strictness, releasing the guard, and marking goals done or verified.
Why use it?
It helps prevent an agent from ending a session before its stated goals are complete, while limiting repeated continuation attempts so it cannot loop forever.

Command

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 commands/publu/goalkeeper/help
Clone the repo
git clone --depth 1 https://github.com/publu/goalkeeper
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 307 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 $0.00010 $0.00307
Opus 5 $0.00005 $0.00153
Sonnet 5 $0.00002 $0.00061
Haiku 4.5 $0.00001 $0.00031

Measured yesterday against content hash 4c5c2ac3c5cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

help 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.

commands/help.md · 29 lines

What it actually says

Explain goalkeeper to the user, concisely:

goalkeeper is a Stop-hook guard for Claude Code & Codex. It won't let this session end until the goals it is holding are provably complete. Every time the agent tries to stop, goalkeeper re-injects the unfinished checklist as the next instruction — so the agent keeps working instead of quitting early.

Commands

  • /goalkeeper:go <objective> — decompose an objective into goals and start working
  • /goalkeeper:add <goal> — add one verifiable goal
  • /goalkeeper:status — show mode and checklist
  • /goalkeeper:mode [off|lite|standard|strict] — get/set strictness
  • /goalkeeper:release — clear all goals and stand the guard down
  • /goalkeeper:help — this message

Modes: off (disarmed) · lite (one nudge) · standard (until done) · strict (until done and independently verified).

Config (env): GOALKEEPER_DEFAULT_MODE sets the starting mode; GOALKEEPER_MAX_LOOPS (default 30) caps continuations without progress so it can never loop forever.

The agent keeps the loop honest by checking goals off as it finishes them: done <id>, and in strict mode verify <id> once there's proof.

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 · 29 lines · 10 tokens per session scan A 4c5c2ac3c5cc

Subscribe to this mod's changes

help is a command published in the GitHub repository publu/goalkeeper (1 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 307 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.