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.
npx agentmods add commands/publu/goalkeeper/modegit clone --depth 1 https://github.com/publu/goalkeeperWhat 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 | $0.00015 | $0.00141 |
| Opus 5 | $0.00008 | $0.00071 |
| Sonnet 5 | $0.00003 | $0.00028 |
| Haiku 4.5 | $0.00002 | $0.00014 |
Grade A, and why
mode scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the following. With no argument it prints the current mode; with an argument it sets it.
node "${CLAUDE_PLUGIN_ROOT}/hooks/goalkeeper-cli.js" mode $ARGUMENTS
Modes:
- off — disarmed; goalkeeper never blocks stopping.
- lite — blocks once with a reminder, then lets you stop.
- standard — blocks until every goal is marked done.
- strict — blocks until every goal is done AND independently verified.
Report the result.
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.
- yesterday First seen · 20 lines · 15 tokens per session scan A 4b9f1116e873
mode is a command published in the GitHub repository publu/goalkeeper (1 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 141 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.
Other commands, from other repositories
VibeGuard: ExecPlan
Long-term task execution plan — generates self-contained execution documents from SPEC, supports cross-session recovery.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
VibeGuard: Live Truth
Verify live claims with fresh facts, inferences, and unresolved gaps.
VibeGuard: Stats
View hooks trigger statistics - interception/warning/release times and reason analysis.
safe-build
Build the application for development or production.
memory
Use when: user asks to remember something, after solving a non-obvious problem, or to capture key session findings.