goal-lock

goal-lock is a skill for Claude Code, Codex from MelonS/MelonS-Agents. It costs 107 tokens per session (1,127 once invoked), scanned A, original, MIT.

A read-only check of the active goal file that lists unfinished deliverables and counts how many remain.

In plain words
What is it for?
It is for checking unchecked items in docs/goal.md and reviewing the stated completion condition before deciding whether to continue.
Why use it?
It makes the remaining work visible during long or automated coding sessions without changing the goal or marking tasks complete.

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/melons/melons-agents/goal-lock
Any agent
npx skills add MelonS/MelonS-Agents --skill goal-lock
Clone the repo
git clone --depth 1 https://github.com/MelonS/MelonS-Agents

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.

agentmods badge for goal-lock

README.md
[![agentmods](https://agentmods.dev/badge/skills/melons/melons-agents/goal-lock.svg)](https://agentmods.dev/skills/melons/melons-agents/goal-lock)
Your own site
<a href="https://agentmods.dev/skills/melons/melons-agents/goal-lock"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/goal-lock.svg" alt="Measured on agentmods" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,127 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 $0.00107 $0.01127
Opus 5 $0.00053 $0.00563
Sonnet 5 $0.00021 $0.00225
Haiku 4.5 $0.00011 $0.00113

Measured 5d ago against content hash f2159a83f011, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goal-lock 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check-done.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/goal-lock/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

goal-lock

A small discipline helper. When an autonomous worker or a long interactive session is advancing the active goal in docs/goal.md, it's useful to know at a glance which deliverable subgoals are still unchecked. That's the entire purpose of this skill.

What this does

Reads the first ### YYYY-MM-DD | ... subsection under ## Active goal in docs/goal.md and lists every - [ ] (unchecked) deliverable subgoal. Also reports the count and the "Done when" line if present.

What this does NOT do

  • Does not alter the Claude Code harness's turn loop. The agent still runs whatever the operator or scheduler invoked.
  • Does not auto-tick subgoals. Operator (or the per-commit hook that ticks subgoals on relevant commits) does that.
  • Does not enforce any policy. This is read-only reporting. If the operator wants autonomous mode to halt when all subgoals are checked, they wire scripts/check-done.sh's exit code into their AUTONOMY_MODE driver.

Why this exists

docs/goal.md "Done when" criteria are prose plus a list of deliverable subgoals. Without a one-liner check, a long autonomous session has to either (a) re-read the entire goal file between iterations or (b) drift past the goal because no one re-checked completion. This skill makes the check a single bash call.

Invocation

# Default — list unchecked subgoals + counts
bash skills/goal-lock/scripts/check-done.sh

# One-line summary
bash skills/goal-lock/scripts/check-done.sh --quiet

# Machine-readable JSON
bash skills/goal-lock/scripts/check-done.sh --json

Exit codes:

  • 0 — at least one subgoal remains unchecked (work is still to do)
  • 1 — all subgoals are checked (goal is probably done; the Done when prose may add further conditions the operator must read manually)
  • 2docs/goal.md missing, malformed, or active goal section empty

How autonomous mode can use this

The recommended pattern for an autonomous loop is to call check-done.sh after each iteration:

Read the full file on GitHub · 113 lines

Files

What ships with it

1 file 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.

  1. 5d ago First seen · 113 lines · 107 tokens per session scan A f2159a83f011

Subscribe to this mod's changes

goal-lock is a skill published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 13d ago), licensed MIT. It adds 107 tokens to every session and 1,127 once invoked, about $0.0005 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 2026-08-30.