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/gogit 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 | $0.00019 | $0.00301 |
| Opus 5 | $0.00010 | $0.00151 |
| Sonnet 5 | $0.00004 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
go 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 2d 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.
What it actually says
The user wants goalkeeper to hold this session to an objective:
$ARGUMENTS
Do the following, in order:
-
Decompose the objective into a short list of concrete, independently verifiable goals — each one a thing you can point at and prove is finished (a file exists, a test passes, a command exits 0). Prefer 2–6 goals. Avoid vague goals like "make it good"; prefer "all unit tests pass".
-
Record each goal:
node "${CLAUDE_PLUGIN_ROOT}/hooks/goalkeeper-cli.js" add "<goal text>" -
Confirm the mode is armed. If
goalkeeper-cli.js statusreportsmode=off, set it:goalkeeper-cli.js mode standard(orstrictif the user wants every goal double-checked before it counts). -
Start working immediately. Do not stop to ask permission. As each goal is genuinely finished, mark it
done <id>(and in strict mode,verify <id>once you have concrete proof). goalkeeper will block any attempt to stop while goals remain open, and will release you automatically the moment the checklist is empty.
Begin now.
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.
- 2d ago First seen · 31 lines · 19 tokens per session scan A d5800a52db6f
go is a command published in the GitHub repository publu/goalkeeper (1 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 301 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: Cross Review
Dual-model adversarial review — Claude generates review reports, Codex does adversarial verification, and iterates until convergence.
VibeGuard: ExecPlan
Long-term task execution plan — generates self-contained execution documents from SPEC, supports cross-session recovery.
VibeGuard: Preflight
Explore the project before major modifications, generate constraint sets, and prevent problems from the source.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
VibeGuard: Build Fix
Build repair — read build errors, locate root causes, perform minimal repairs, and verify that the build passed.
safe-build
Build the application for development or production.