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 skills add OmidZamani/dspy-skills --skill dspy-finetune-bootstrapgit clone --depth 1 https://github.com/OmidZamani/dspy-skillsWrote 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/omidzamani/dspy-skills/dspy-finetune-bootstrap)<a href="https://agentmods.dev/skills/omidzamani/dspy-skills/dspy-finetune-bootstrap"><img src="https://agentmods.dev/badge/skills/omidzamani/dspy-skills/dspy-finetune-bootstrap/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/omidzamani/dspy-skills/dspy-finetune-bootstrap"><img src="https://agentmods.dev/badge/skills/omidzamani/dspy-skills/dspy-finetune-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.01825 |
| Opus 5.5 | $0.00014 | $0.00730 |
| Sonnet 5.5 | $0.00007 | $0.00365 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
dspy-finetune-bootstrap 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 1mo 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DSPy BootstrapFinetune Optimizer
Goal
Distill a DSPy program into fine-tuned model weights for efficient production deployment.
When to Use
- You have a working DSPy program with a large model
- Need to reduce inference costs
- Want faster responses (smaller model)
- Deploying to resource-constrained environments
Inputs
| Input | Type | Description |
|---|---|---|
program |
dspy.Module |
Teacher program to distill |
trainset |
list[dspy.Example] |
Training examples |
metric |
callable |
Validation metric (optional) |
train_kwargs |
dict |
Training hyperparameters |
Outputs
| Output | Type | Description |
|---|---|---|
finetuned_program |
dspy.Module |
Program with fine-tuned weights |
model_path |
str |
Path to saved model |
Workflow
Phase 1: Prepare Teacher Program
import dspy
# Configure with strong teacher model
dspy.configure(lm=dspy.LM("openai/gpt-4o"))
class TeacherQA(dspy.Module):
def __init__(self):
self.cot = dspy.ChainOfThought("question -> answer")
def forward(self, question):
return self.cot(question=question)
Phase 2: Configure Fine-Tuning
Assign the LM directly to predictors before fine-tuning:
import dspy
from dspy.teleprompt import BootstrapFinetune
optimizer = BootstrapFinetune(
metric=lambda gold, pred, trace=None: gold.answer.lower() in pred.answer.lower(),
train_kwargs={
'learning_rate': 5e-5,
'num_train_epochs': 3,
'per_device_train_batch_size': 4,
'warmup_ratio': 0.1
}
)
Phase 3: Fine-tune Student Model
teacher = TeacherQA()
teacher.set_lm(dspy.settings.lm)
finetuned = optimizer.compile(teacher, trainset=trainset)
Phase 4: Deploy
# Save the fine-tuned model (saves state-only by default)
finetuned.save("finetuned_qa_model.json")
# Load and use (must recreate architecture first)
loaded = TeacherQA()
loaded.load("finetuned_qa_model.json")
result = loaded(question="What is machine learning?")
What ships with it
1 file 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.
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.
- 1mo ago First seen · 254 lines · 35 tokens per session scan A 4a6866192006
dspy-finetune-bootstrap is a skill published in the GitHub repository OmidZamani/dspy-skills (124 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,825 once invoked, about $0.0001 per session on Opus 5.5. 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
evolving-ai-agents
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
ai-data-steward
Creates a minimal, sourced, versioned context contract for AI-assisted work across teams, including freshness, quality checks, permitted use, and correction ownership. Use when the user says "teams have different facts", "clean up shared AI context", "make this dataset usable", or "stop stale context reaching Sales".
reverse-information-paradox
Diagnoses how consuming external AI forces you to reveal proprietary knowledge — your 'intelligence exhaust' (prompts, tool calls, corrections, evals) — to whoever controls the learning infrastructure, and prescribes a trust boundary that keeps your data, evals, memory, adapted weights, and learning loops inside your…
mcp-builder
Scaffolds and ships MCP servers in Python (FastMCP) or TypeScript (@modelcontextprotocol/sdk) — tools designed around workflows rather than raw endpoints, with model-guiding schemas and error messages, pagination, a direct-call test harness, and wiring into .mcp.json or claude mcp add. Use when the user says "build an…
dspy
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming.