Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MelonS/MelonS-Agentsnpx agentmods add skills/melons/melons-agents/goal-lockWrote 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.
[](https://agentmods.dev/skills/melons/melons-agents/goal-lock)<a href="https://agentmods.dev/skills/melons/melons-agents/goal-lock"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/goal-lock/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00107 | $0.01127 |
| Opus 5.5 | $0.00043 | $0.00451 |
| Sonnet 5.5 | $0.00021 | $0.00225 |
| Haiku 4.5 | $0.00011 | $0.00113 |
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 2mo 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.
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 theirAUTONOMY_MODEdriver.
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; theDone whenprose may add further conditions the operator must read manually)2—docs/goal.mdmissing, 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:
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.
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 · 113 lines · 107 tokens per session scan A f2159a83f011
goal-lock is a skill published in the GitHub repository MelonS/MelonS-Agents (17 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,127 once invoked, about $0.0004 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.
Other skills, from other repositories
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
refactor-clean
Refactor cleanly instead of layering sediment. Use for rename requests, stale or misleading names, legacy leftovers, changed scope, or when a change reveals duplicated concepts, local adapters, obsolete owners, redundant inputs or guards, compatibility wrappers, parallel abstractions, an over-large module that has…