Borrowing it
Nothing to install: this file belongs to compozy/kb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/compozy/kb/main/.agents/skills/to-prompt/SKILL.mdgit clone --depth 1 https://github.com/compozy/kbWrote 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/compozy/kb/to-prompt)<a href="https://agentmods.dev/skills/compozy/kb/to-prompt"><img src="https://agentmods.dev/badge/skills/compozy/kb/to-prompt/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/compozy/kb/to-prompt"><img src="https://agentmods.dev/badge/skills/compozy/kb/to-prompt.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.00468 |
| Opus 5.5 | $0.00014 | $0.00187 |
| Sonnet 5.5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
to-prompt 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 25d 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.
What it actually says
To Prompt
Write a brief, not a solution. The brief carries everything the receiving LLM needs to choose the implementation itself — the problem, the current state, the requirements, the constraints — and preserves any implementation constraints or approved plan already supplied by the user. Leave undecided design choices to the receiver; do not erase accepted decisions to manufacture an open-ended problem.
Every brief is a file: docs/prompts/<YYYYMMDD-HHmm>_<slug>.md (e.g. docs/prompts/20260709-1745_fix-auth-redirect.md).
Steps
- Classify the task — bug fix, improvement, or feature — and draft a one-paragraph statement of the problem and the outcome wanted.
- Gather the evidence. Read the code paths involved; quote current code as it exists; capture the relevant error/log excerpts, excluding credentials and unrelated private data; note environment and recent changes. Done when: every claim in the brief is backed by something you actually read or ran.
- Write the brief from the template. Copy
assets/brief-template.mdtodocs/prompts/<YYYYMMDD-HHmm>_<slug>.md(create the directory if absent; slug = lowercase-hyphenated summary; timestamp = now). Fill the applicable sections and remove guidance comments. Record consequential unknowns; omit irrelevant sections. - Check decision fidelity. Separate user-approved constraints from suggestions and unresolved choices. Preserve the requested outcome and authorization; avoid introducing new implementation mandates.
- Hand off. Reply with the file path and a one-line summary of what the brief asks for.
Bundled files
assets/brief-template.md— the brief's skeleton and per-type coverage guidance; the single source of truth for what a complete brief contains.
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.
- 25d ago First seen · 27 lines · 36 tokens per session scan A 34e9b869d18f
to-prompt is a skill published in the GitHub repository compozy/kb (112 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 468 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 2026-09-26.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…