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 commands/thatsuperdev/distill-prompts/distillgit clone --depth 1 https://github.com/thatsuperdev/distill-promptsWrote 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/commands/thatsuperdev/distill-prompts/distill)<a href="https://agentmods.dev/commands/thatsuperdev/distill-prompts/distill"><img src="https://agentmods.dev/badge/commands/thatsuperdev/distill-prompts/distill.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 | $0.00016 | $0.02500 |
| Opus 5 | $0.00008 | $0.01250 |
| Sonnet 5 | $0.00003 | $0.00500 |
| Haiku 4.5 | $0.00002 | $0.00250 |
Grade A, and why
distill 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 — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill
A universal AI skill that turns vague, messy, or under-specified user requests into clearer, more useful instructions before solving them.
Distill does not exist to make prompts longer. It exists to preserve the user's intent, reduce ambiguity, add structure only when useful, and help the underlying AI produce a better result with less waste.
Use it with:
/distill fix this bug
@distill help me migrate this project
distill this: review my API design
Use Distill before answering: explain why this test fails
Invocation modes
Distill supports two invocation modes. The behavior — modes, profiles, restraint rules — is identical in both.
Explicit mode (default)
Triggered manually with /distill, @distill, or distill this:. Does nothing on other requests.
Always-on mode
Applied automatically to every request. When a request is already clear, Distill passes through without rewriting. When the input is noisy, vague, or complex, it distills first.
To skip Distill on a single request in always-on mode, prefix with --raw:
--raw just tell me what this function returns
To disable always-on globally, remove the always-on snippet from your CLAUDE.md or equivalent config file.
See the README for setup instructions per platform.
Core instruction
When Distill is invoked, do not immediately solve the user's request.
First, transform the request into the most useful execution form for the current AI model, task type, and available context.
Then proceed using the distilled version unless the user explicitly asks to only produce the distilled request.
Distill must behave like a careful editor, not a prompt bloat generator.
Prime directive
Preserve the user's intent.
Improve only what helps the AI understand, plan, execute, verify, or explain the task better.
Do not add requirements the user did not ask for or clearly imply.
Do not overcomplicate simple requests.
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 · 527 lines · 16 tokens per session scan A 18a6a8aa6760
distill is a command published in the GitHub repository thatsuperdev/distill-prompts (1 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 2,500 once invoked, about $0.0001 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 commands, from other repositories
architect
Activate the Prompt Architect agent to design sophisticated prompts using advanced reasoning patterns.
harvest
Activate the Prompt Harvester agent to discover and collect elite prompts from various sources.
evolve
Activate the Prompt Evolver agent to improve prompts based on research, metrics, and new techniques.
speckit.specjudge.recommend
Recommend the model that fits this feature's tasks, with the fragment of the spec behind every level.
setup-models
Update the default LLM provider and model, optionally validate provider connectivity with a test API call.
setup-routing
Configure per-task LLM routing for Gnosys tasks.