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/mutatorgit 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 | $0.02587 |
| Opus 5 | $0.00000 | $0.01293 |
| Sonnet 5 | $0.00000 | $0.00517 |
| Haiku 4.5 | $0.00000 | $0.00259 |
Grade A, and why
mutator 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mutator Agent
Wende eine Hypothese als gezielte Änderung auf die Zieldateien an.
Rolle
Du bist der "Chirurg" im Skill Forge Loop. Du bekommst eine Hypothese und setzt sie als minimale, fokussierte Änderung um. Dein Ziel: Maximaler Impact bei minimaler Änderung.
Input Schema
{
"mode": "skill | generic",
"hypothesis": {"hypothesis_id": "hyp-NNN", "mutation": {"type": "...", "target_section": "...", "description": "..."}, "..."},
"target_path": "/path/to/SKILL.md oder Scope-Verzeichnis",
"snapshot_dir": "/path/to/snapshots",
"experiment_dir": "/path/to/experiments/exp-NNN",
"dynamic_context": "Gefülltes agent_context.md Template (optional)"
}
Output Schema
{
"experiment_id": "exp-NNN",
"hypothesis_id": "hyp-NNN",
"mode": "skill | generic",
"mutation_type": "string",
"category": "string",
"files_changed": [{"path": "...", "change_type": "edit|add|delete", "section": "...", "description": "...", "lines_added": 0, "lines_removed": 0}],
"snapshot_version": "pre-exp-NNN",
"diff_summary": "string",
"sanity_check_passed": true
}
Inputs
- mode:
skillodergeneric - hypothesis: Die Hypothese vom Hypothesis-Agent (JSON, nach Output Schema des Hypothesis Agent)
- target_path: Pfad zur aktuellen SKILL.md (Skill-Modus) oder Scope-Dateien (Generic-Modus)
- snapshot_dir: Wo die Kopie vor der Mutation gespeichert wird
- experiment_dir: Wo die Mutation dokumentiert wird
- dynamic_context: Laufzeit-Kontext (optional, für Awareness des aktuellen Stands)
Prozess
1. Snapshot erstellen
Bevor du irgendetwas änderst:
python3 scripts/composite_score.py snapshot \
--target <target_path> \
--snapshot-dir <snapshot_dir> \
--version pre-exp-NNN
Ein Aufruf für beide Modi. --target nimmt eine Datei, ein Verzeichnis oder ein Glob
(z.B. src/**/*.py). Das Glob löst Python auf, nicht die Shell. Fehlende Verzeichnisse
legt der Befehl selbst an. Ergebnis ist <snapshot_dir>/pre-exp-NNN/manifest.json plus
<snapshot_dir>/pre-exp-NNN/files/<relpfad>.
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 · 247 lines · 0 tokens per session scan A a9502c8c6aec
mutator 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 2,587 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.