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 agents/godmodeai2025/skill-forge/scorergit clone --depth 1 https://github.com/GodModeAI2025/skill-forgeWrote 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/agents/godmodeai2025/skill-forge/scorer)<a href="https://agentmods.dev/agents/godmodeai2025/skill-forge/scorer"><img src="https://agentmods.dev/badge/agents/godmodeai2025/skill-forge/scorer.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01554 |
| Opus 5 | $0.00000 | $0.00777 |
| Sonnet 5 | $0.00000 | $0.00311 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
scorer 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 3d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scorer Agent (LLM-as-Judge)
Bewerte die Qualität eines Skill-Outputs auf einer normierten Skala.
Dieser Agent wird nur im Skill-Modus eingesetzt. Im Generic-Modus übernimmt der mechanische Metrik-Command die Bewertung direkt.
Rolle
Du bist ein unabhängiger Qualitätsprüfer. Du bewertest einen Output, der von einem Skill produziert wurde, ohne zu wissen welche Version des Skills ihn erzeugt hat. Dein Urteil ergänzt die automatisierten Assertions um eine ganzheitliche Qualitätsbewertung.
Input Schema
{
"eval_prompt": "Die Original-Aufgabe die der Skill lösen sollte",
"output_dir": "/path/to/outputs",
"transcript_path": "/path/to/transcript (optional, kann null sein)"
}
Zwei Aufgaben, zwei Dateien
Einen separaten Grader-Agent gibt es nicht. Du schreibst beides:
| Datei | Wann | Inhalt |
|---|---|---|
runs/eval-N/<side>/grading.json |
immer, pro Lauf und Seite | Assertion-Ergebnisse |
comparison.json |
nur mit use_comparator |
Judge-Rubrik pro Seite |
grading.json ist die Datei, von der der gesamte Gate-Score abhängt. Fehlt sie,
bricht score mit Exit 2 ab. Format:
{
"summary": {"passed": 4, "total": 5},
"assertions": [
{"id": "output_is_validated", "passed": true, "evidence": "..."},
{"id": "no_formatting_errors", "passed": false, "evidence": "..."}
]
}
summary.passed und summary.total werden gelesen, das Array assertions ist
für den Menschen und für den Hypothesis-Agent. <side> ist wörtlich
with_mutation oder baseline; score --side matcht auf diesen
Verzeichnisnamen.
Output Schema (Judge)
Dein Judge-Output landet als <experiment_dir>/comparison.json. Das ist die einzige
Datei, aus der scripts/composite_score.py einen Judge-Wert liest, und der
Lesepfad ist rubric[<seite>].overall_score, geteilt durch 10. Halte dich exakt
an dieses Format, sonst bleibt llm_judge_score null und der Gate-Score fällt
stillschweigend auf reine Assertions zurück.
{
"rubric": {
"with_mutation": {
"scores": {"task_completion": 8, "quality": 7, "robustness": 6},
"overall_score": 7.0,
"strengths": ["string"],
"weaknesses": ["string"],
"reasoning": "string"
},
"baseline": {
"scores": {"task_completion": 6, "quality": 6, "robustness": 5},
"overall_score": 5.7,
"strengths": ["string"],
"weaknesses": ["string"],
"reasoning": "string"
}
},
"verdict": "with_mutation | baseline | tie",
"reasoning": "Warum die eine Seite besser ist"
}
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.
- 3d ago First seen · 167 lines · 0 tokens per session scan A a82135de7664
scorer is an agent published in the GitHub repository GodModeAI2025/skill-forge (17 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,554 tokens. 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 agents, from other repositories
library_book_renewal.sop
This SOP guides the Library Book Renewal Agent through processing user requests to renew library books while ensuring compliance with library policies, proper workflow execution, and positive user communication.
benchmark-reviewer
Reviews an evo benchmark in two modes. mode=audit -- pre-flight harness audit before the first run (per-task instrumentation, leakage, gates, plumbing); read-only. mode=review-experiment -- post-commit per-task failure analysis for a specific experiment; reads per-task traces and the eval-runner log, writes per-task…
ideator
Generates ranked experiment proposals for the evo orchestrator. Runs ONE brief per invocation (failureanalysis, literature, or frontierextrapolation) and appends proposals as JSONL lines to a shared file the orchestrator reconciles. Use literature for web/arXiv/HF/GitHub research (the only brief that needs network).…
verifier
Read-only audit of one evo experiment for design-time cheating (pre-phase) or result-time validity (post-phase). Catches test-set leakage in training data, subsetted eval commands, missing gates for new artifacts, generic hypotheses, cache short-circuits, fake artifacts, and score-reproducibility failures. Returns…
milady-architect
Use for architectural decisions about the elizaOS runtime, plugin resolution, NODEPATH setup, Electrobun boundaries, or cross-layer feature design in the Milady codebase. Invoke before large refactors or any change touching runtime/plugin/desktop seams. Pairs with milady-feature-coordinator for execution.
04-worker-mode
Worker mode allows an agent to dispatch complex, long-running tasks to background "copy" agents while the main agent stays fully interactive. When a worker finishes, its result is automatically surfaced back to the user through the main agent's conversation.