Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bonfire-systems/goalkeeper/plugin install goalkeeperWrote 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/bonfire-systems/goalkeeper/goal-judge)<a href="https://agentmods.dev/skills/bonfire-systems/goalkeeper/goal-judge"><img src="https://agentmods.dev/badge/skills/bonfire-systems/goalkeeper/goal-judge/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/bonfire-systems/goalkeeper/goal-judge"><img src="https://agentmods.dev/badge/skills/bonfire-systems/goalkeeper/goal-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00083 | $0.01391 |
| Opus 5 | $0.00042 | $0.00696 |
| Sonnet 5 | $0.00017 | $0.00278 |
| Haiku 4.5 | $0.00008 | $0.00139 |
Grade A, and why
goal-judge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are operating the goal-judge skill — the gate that decides whether a goal is actually done, not just superficially passing the validator. The judge is what differentiates goalkeeper from a naive auto-loop.
The gk CLI (python3 "${CLAUDE_PLUGIN_ROOT}/scripts/gk.py", abbreviated gk) does all the mechanical work: brief assembly and verdict application. Your job is spawning the judge and relaying its output faithfully.
Invocation sources
- Inline mode — the
/goalskill's execution loop auto-fires the judge when the validator passes. - Subagent mode — the
/goal-chainorchestrator invokes the judge AFTER the executor subagent returns withSTATUS: validator_pass. The executor never invokes the judge itself. - Advisory on-demand — user runs
/goal-judgedirectly for a non-binding read on an in-progress goal (does not advance state).
The verdict logic and grading rubric are identical across all three — they are baked into the brief that gk judge-brief emits. Only the invocation context differs.
Step 1 — assemble the brief
gk judge-brief <slug> [--executor-summary <file>]
This emits the complete, self-contained judge prompt: contract verbatim, compacted log, diff scope (git baseline, pre-existing dirty paths, validator baseline subtraction), the deduped file list to read end-to-end, the filtered diff (lockfiles/build outputs/IDE files excluded, plus contract diff_excludes), and the verdict-format instructions — including the requirement that every MET verdict cites file:line evidence.
In subagent mode (chain-driven), first write the executor's structured return (STATUS / SUMMARY / VALIDATOR_OUTPUT_TAIL / FILES_CHANGED) to a scratch file and pass it via --executor-summary — the brief marks it as a leading hint the judge must independently verify.
Do not edit, trim, or "improve" the brief. Comparable verdicts across runs require identical prompt shape — that is the whole reason assembly is mechanical.
Step 2 — run the judge
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.
- 11d ago First seen · 79 lines · 83 tokens per session scan A b56c663fca06
goal-judge is a skill published in the GitHub repository bonfire-systems/goalkeeper (13 stars, last pushed 11d ago), licensed MIT. It adds 83 tokens to every session and 1,391 once invoked, about $0.0004 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.
Other skills, from other repositories
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
verification-engine
Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
eval-grader
Measure output quality, don't vibe it: score a generative task with a two-layer grader — deterministic code metrics + per-dimension LLM-as-judge — over a fixed task set, as signed deltas vs a pinned baseline. Grades cost alongside correctness (pass-slow).
testing
The how of testing: pyramid, AAA, isolation, risk coverage, determinism. Guarantees the DoD's "tests are green". test-expert-csk applies it. Use when writing or changing tests, or when a suite is flaky, slow or green for the wrong reason.