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 skills/profsynapse/synaptic-tuner/synethetic-data-generationnpx skills add ProfSynapse/Synaptic-Tuner --skill synethetic-data-generationgit clone --depth 1 https://github.com/ProfSynapse/Synaptic-TunerWrote 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/profsynapse/synaptic-tuner/synethetic-data-generation)<a href="https://agentmods.dev/skills/profsynapse/synaptic-tuner/synethetic-data-generation"><img src="https://agentmods.dev/badge/skills/profsynapse/synaptic-tuner/synethetic-data-generation.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 | $0.00086 | $0.05229 |
| Opus 5 | $0.00043 | $0.02615 |
| Sonnet 5 | $0.00017 | $0.01046 |
| Haiku 4.5 | $0.00009 | $0.00523 |
Grade A, and why
synthetic-data-generation 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 5d 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SynthChat: Synthetic Data Generation
Generate, improve, validate, sanitize, and evaluate synthetic training datasets via CLI and YAML configuration.
Quick Reference
| Task | Command |
|---|---|
| Generate dataset | python -m SynthChat.run generate [options] |
| Generate with prompt optimization overlay | python -m SynthChat.run generate --prompt-opt-config configs/prompt_optimization/NAME.yaml [options] |
| Standalone prompt optimization | python tuner.py prompt-optimize --prompt-opt-config configs/prompt_optimization/NAME.yaml |
| Generate with environment runtime checks | python -m SynthChat.run generate --env-backend local [options] |
| Generate with custom tool schema/rules | python -m SynthChat.run generate --env-backend local --env-tool-schema path/to/tool_schema.yaml --env-exec-config path/to/environment_execution.yaml [options] |
| Debug environment generation only | python -m SynthChat.run env-generate --scenario SCENARIO --debug-artifacts [path] [options] |
| Improve dataset | python -m SynthChat.run improve -i FILE [options] |
| Validate dataset | python -m SynthChat.run validate -i FILE [options] |
| Sanitize docs or JSONL | python -m SynthChat.run sanitize -i PATH --privacy-profile PROFILE [options] |
| Evaluate model | python -m Evaluator.cli --model NAME [options] |
| Project rollouts → SFT/KTO/GRPO | python SynthChat/scripts/project_rollout_datasets.py --input ROLLOUT.jsonl --canonical-output ... --kto-output ... --grpo-output ... [--sft-output ...] [--filter-config FILTER.yaml] |
| Structural check | python3 scripts/validate_syngen.py FILE |
| JSONL → Markdown | ./scripts/jsonl_to_markdown.sh data.jsonl |
| Combine datasets | ./scripts/combine_datasets.sh -o out.jsonl FILE1 FILE2 |
| Interactive menu | ./run.sh |
Key Directories
SynthChat/scenarios/— Generation templates (6 files, ~30 scenarios)SynthChat/rubrics/— Quality rubrics (17 files)SynthChat/config/—settings.yaml,validation.yamlEvaluator/config/environment_execution.yaml— Runtime action inference rules (config-driven)Datasets/synthchat/— Generated datasets go here (dry-runs and full runs)SynthChat/interactions/— Judge/improve logs
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/cli-commands.md 12 KB
- reference/manual-editing.md 2.6 KB
- reference/rollout-projection.md 11 KB
- reference/rubric-authoring.md 4.8 KB
- reference/scenario-authoring.md 14 KB
- reference/settings-config.md 7.0 KB
- reference/testing-protocol.md 19 KB
- scripts/combine_datasets.sh 4.2 KB runs code
- scripts/dry_run.sh 1.7 KB runs code
- scripts/jsonl_to_markdown.sh 5.7 KB runs code
- scripts/validate_syngen.py 30 KB runs code
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.
- 5d ago First seen · 438 lines · 86 tokens per session scan A b54d94b010ca
synthetic-data-generation is a skill published in the GitHub repository ProfSynapse/Synaptic-Tuner (27 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 5,229 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
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.