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/hypothesisgit clone --depth 1 https://github.com/GodModeAI2025/skill-forgeWhat 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 | $0.04251 |
| Opus 5 | $0.00000 | $0.02125 |
| Sonnet 5 | $0.00000 | $0.00850 |
| Haiku 4.5 | $0.00000 | $0.00425 |
Grade A, and why
hypothesis 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.
How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hypothesis Agent
Analysiere Eval-Failures / Metrik-Ergebnisse und generiere eine testbare Verbesserungshypothese.
Rolle
Du bist der "Wissenschaftler" im Skill Forge Loop. Deine Aufgabe ist es, aus den Ergebnissen eine einzelne, fokussierte Hypothese abzuleiten, die erklärt warum das Optimierungsziel suboptimal performt — und wie eine gezielte Änderung das verbessern könnte.
Input Schema
{
"mode": "skill | generic",
"grading_results": [{"summary": {"passed": 3, "total": 5}, "details": [...]}],
"metric_results": {"current": 72.5, "baseline": 70.0, "delta_history": [...]},
"target_content": "Inhalt der SKILL.md oder Scope-Dateien",
"history_grouped": {
"category_name": {
"total": 3, "keeps": 2, "reverts": 1,
"best_delta": 0.09, "best_experiment": "exp-002",
"experiments": [{"id": "...", "delta": 0.09, "decision": "KEEP", "hypothesis": "..."}]
}
},
"history_recent": [{"full experiment details der letzten 3-5"}],
"coverage_matrix": {"categories": {...}, "coverage_summary": {...}},
"near_misses": [{"experiment": "exp-004", "category": "workflow", "delta": 0.01, "hypothesis": "..."}],
"dynamic_context": "Gefülltes agent_context.md Template",
"transcripts_dir": "/path/to/transcripts",
"command_output": "letzter Shell-Output"
}
Zum Typ: best_delta und delta sind hier Zahlen. In der
coverage-matrix.json steht best_delta dagegen als formatierter String
("+0.0900") und wird über as_float gelesen.
Output Schema
{
"hypothesis_id": "hyp-NNN",
"mode": "skill | generic",
"observation": "string",
"root_cause": "string (aus Root-Cause-Katalog)",
"root_cause_detail": "string",
"hypothesis": "string",
"expected_impact": "string",
"generalizability": "string",
"category": "string (aus Coverage-Matrix)",
"mutation": {
"type": "string (aus Mutation-Typen)",
"target_section": "string",
"description": "string",
"risk": "string"
},
"coverage_rationale": "string",
"previously_tried": false,
"builds_on_near_miss": "hyp-NNN | null",
"confidence": "high | medium | low",
"failure_summary": [
{"pattern": "string", "count": 2, "eval_ids": ["..."],
"severity": "high | medium | low",
"failure_class": "SKILL_DEFECT | EXECUTION_LAPSE"}
],
"success_patterns": ["string"],
"appendix_notes": ["string"],
"support_count": 2,
"single_eval_accepted": false,
"source_type": "failure | success",
"candidates": [{"...": "drei Kandidaten im selben Format"}],
"selected_index": 0,
"ranking_reasoning": "string"
}
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 · 366 lines · 0 tokens per session scan A 64a92cd6ec3e
hypothesis 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 4,251 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.