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 agentsope/SkillAlchemy --skill agentsop-signature-designgit clone --depth 1 https://github.com/agentsope/SkillAlchemyWrote 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/agentsope/skillalchemy/agentsop-signature-design)<a href="https://agentmods.dev/skills/agentsope/skillalchemy/agentsop-signature-design"><img src="https://agentmods.dev/badge/skills/agentsope/skillalchemy/agentsop-signature-design/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/agentsope/skillalchemy/agentsop-signature-design"><img src="https://agentmods.dev/badge/skills/agentsope/skillalchemy/agentsop-signature-design.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 | $0.00226 | $0.05381 |
| Opus 5 | $0.00113 | $0.02691 |
| Sonnet 5 | $0.00045 | $0.01076 |
| Haiku 4.5 | $0.00023 | $0.00538 |
Grade A, and why
agentsop-signature-design 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 11d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Signature-Design — Promote Prose → Typed Contract
"DSPy uses the field names as the only natural-language hint the optimizer has about intent before it sees data. Name them like you'd name function parameters in well-written code." — derived from [dspy.ai/learn/programming/signatures/], see
references/R1-source-evidence.md
This skill is the decision layer, not the library layer. It tells you when a prose prompt has become
"load-bearing" enough to deserve a typed Signature, and how to shape its fields. For the actual API
(dspy.Signature, InputField, OutputField, Predict, ChainOfThought, compile, save) defer to the
[[dspy]] skill; for the full program→evaluate→optimize SOP defer to [[agentsop-dspy]].
1. 何时激活 (When to activate)
Activate this overlay the moment a hand-written prompt crosses any one of three load-bearing thresholds.
| Trigger | Concrete signal | Why it matters |
|---|---|---|
| Length | A single prompt string grows past ~50 lines of f-string / template | Long prose prompts hide their I/O contract inside narration; the [[agentsop-dspy]] skill names this exact symptom: "hand-written prompts grow past ~50 lines; brittleness on model swap" (R1, claim S1) |
| Code-consumed output | The LM response is parsed, branched on, or stored by downstream code (not just shown to a human) | If code reads the output, the output has a type. An untyped prompt forces brittle regex/JSON-scraping at every call site |
| Reuse | The same prompt (or a copy-pasted variant) is called from >1 call site or in a loop | Reuse means the contract is now an API surface. Drift between copies is a guaranteed bug source |
Secondary signals (each strengthens, none alone is sufficient):
- The prompt is about to be model-swapped (GPT → Llama) and you fear it will break — Signatures + recompile is the documented fix (
R1, claim S6; see [[agentsop-dspy]] Case B). - A metric already exists for this task — you are one step from optimization, and optimizers require a Signature.
- The prompt mixes task instruction + few-shot demos + format spec in one blob — Signatures separate these cleanly.
What ships with it
3 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.
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.
- 11d ago First seen · 321 lines · 226 tokens per session scan A d6cc58c20f89
agentsop-signature-design is a skill published in the GitHub repository agentsope/SkillAlchemy (385 stars, last pushed 8d ago), licensed MIT. It adds 226 tokens to every session and 5,381 once invoked, about $0.0011 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
prompt-refine
Silently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads…
build-dotnet-agent-service
Build a local-first F# or C# Semantic Kernel agent service with explicit tools, model capability checks, evaluation fixtures, and draft-before-write promotion.
prompt-evaluation-runner
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
prompt-perturb
An idea-generation tool that fetches creative prompts from outside sources after removing project-specific context from the search.
prompt-decorators
Activates a structured decorator framework that modifies how Claude reasons, responds, and formats output. Trigger this skill whenever a prompt contains one or more markers prefixed with +++, such as +++Reasoning, +++StepByStep, +++Tone(style=formal), or any other +++ marker, regardless of what follows in the prompt.…
vibe-creating-prompt
Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover…