Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nicobailon/pi-prompt-template-modelnpx agentmods add skills/nicobailon/pi-prompt-template-model/prompt-template-authoringWrote 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/nicobailon/pi-prompt-template-model/prompt-template-authoring)<a href="https://agentmods.dev/skills/nicobailon/pi-prompt-template-model/prompt-template-authoring"><img src="https://agentmods.dev/badge/skills/nicobailon/pi-prompt-template-model/prompt-template-authoring/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/nicobailon/pi-prompt-template-model/prompt-template-authoring"><img src="https://agentmods.dev/badge/skills/nicobailon/pi-prompt-template-model/prompt-template-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 4 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00047 | $0.01361 |
| Opus 5 | $0.00023 | $0.00681 |
| Sonnet 5 | $0.00009 | $0.00272 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
prompt-template-authoring 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 12d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Template Authoring
Use this skill when working on prompt templates for pi-prompt-template-model.
Templates are markdown files that register as slash commands.
Where Templates Live
~/.pi/agent/prompts/— user prompts (highest priority).pi/prompts/inside a trusted project — project-specific prompts
Extension examples/ are reference files only. Copy them to a prompt directory to register them.
Minimal Template
---
model: claude-sonnet-4-20250514
---
Your prompt body here.
Save as my-command.md, restart Pi, run /my-command. Use description: for autocomplete text.
Model Selection
Omit model: to inherit the current session model. Otherwise:
model: claude-sonnet-4-20250514— specific modelmodel: claude-opus-4, gpt-5.4— fallback order (tries first, falls back to second if unavailable)model: claude-opus-4, gpt-5.4+rotate: true— cycle through list on each loop iteration
Argument Substitution
The prompt body can use placeholders:
$@— all arguments passed to the command$1,$2— specific positional arguments${@:1}— argument 1 and everything after
Deterministic Steps (Pre-LLM Execution)
Run a command or script before the LLM turn. The model only sees the output if you want it to.
Two equivalent forms. Don't mix them in the same prompt.
Shorthand form — top-level keys:
---
run: git status --short
handoff: always
---
Summarize the repo state.
Nested form — under deterministic::
---
deterministic:
run: ./scripts/ship.sh
handoff: on-failure
timeout: 60000
---
Diagnose the failure and suggest a fix.
Handoff controls when the LLM sees the result:
never— run, show result, done (no LLM turn)always— always hand result to modelon-failure— only hand off if command exits non-zeroon-success— only hand off if command exits zero
Execution forms:
run: command string— runs via/bin/bash -lcrun: {command: git, args: [status], shell: false}— explicit args, optional shellscript: ./script.shorscript: {path: ./script.sh, args: [--fast]}— run a file
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.
- 12d ago First seen · 190 lines · 47 tokens per session scan A 429335d69679
prompt-template-authoring is a skill published in the GitHub repository nicobailon/pi-prompt-template-model (309 stars, last pushed 14d ago), licensed MIT. It adds 47 tokens to every session and 1,361 once invoked, about $0.0002 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
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…