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/greyok00/slimtoken/prompt-reframenpx skills add greyok00/slimtoken --skill prompt-reframegit clone --depth 1 https://github.com/greyok00/slimtokenWrote 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/greyok00/slimtoken/prompt-reframe)<a href="https://agentmods.dev/skills/greyok00/slimtoken/prompt-reframe"><img src="https://agentmods.dev/badge/skills/greyok00/slimtoken/prompt-reframe.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 | $0.00088 | $0.01148 |
| Opus 5 | $0.00044 | $0.00574 |
| Sonnet 5 | $0.00018 | $0.00230 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
prompt-reframe 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prompt-reframe
A pure-CPU toolkit for tightening natural-language prompts. No LLM
roundtrip; every stage is a deterministic transform that runs in
microseconds. Lives in slimtoken.prompt_reframe and is also exposed
as a standalone MCP server (slimtoken-reframe-mcp).
When to use
- The user prompt is full of "can you basically just..." and repeats itself; the actual ask is buried.
- A batch job needs to fan out N requests with consistent shape; the rewriter gives every prompt the same terse form.
- A product embeds a model and the system prompt is bloated.
- You'd like to know the domain of a request (business / code / osint / cybersecurity / professional / general) before deciding which system prompt to attach.
- You're a small CPU environment (edge device, serverless cold start, batch worker) and can't afford to call a model just to paraphrase.
When NOT to use
- The prompt is already short (< 80 words) and clean. The reframe is a no-op there; you'd just be paying CPU for nothing.
- The user wants the model to handle nuance, hedging, or conversational style. The rewriter strips style on purpose.
- You need a semantic rewrite that the input doesn't already contain. Use an LLM for that; this toolkit only works with sentences that already exist in the input.
How to use
Default — the Python API (works anywhere slimtoken is installed):
from slimtoken.prompt_reframe import (
classify_domain, reframe_prompt, shrink_prompt,
minify_prompt, build_system, frame_prompt,
)
domain = classify_domain(user_prompt)
tight = shrink_prompt(user_prompt, mode='balanced') # ~50 words
system = build_system(domain, role='generalist', style='terse')
# Or one call for the full pipeline:
reframed, system, domain = frame_prompt(user_prompt, mode='balanced')
Fallback — CLI (when you just want to see the effect):
python -m slimtoken.prompt_reframe "your rambling prompt here"
python -m slimtoken.prompt_reframe smoke # built-in tests
python -m slimtoken.prompt_reframe json "your prompt" # machine-readable
What ships with it
2 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.
- 5d ago First seen · 115 lines · 88 tokens per session scan A 516c82c71edd
prompt-reframe is a skill published in the GitHub repository greyok00/slimtoken (4 stars, last pushed 11d ago), licensed MIT. It adds 88 tokens to every session and 1,148 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 2026-08-31.
Other skills, from other repositories
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.
instructor
Structured LLM outputs validated with Pydantic.
guidance
Constrain LLM output with grammars; guarantee valid JSON.
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
promptfoo-evals
Write, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions, model-graded rubrics, transforms, datasets, exports, and CI gates. Use for non-redteam eval coverage, regression tests, or new eval matrices. Do not use for adversarial redteam plugin or strategy…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.