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.
git clone --depth 1 https://github.com/punt-labs/prfaqWrote 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/agents/punt-labs/prfaq/streamliner)<a href="https://agentmods.dev/agents/punt-labs/prfaq/streamliner"><img src="https://agentmods.dev/badge/agents/punt-labs/prfaq/streamliner/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/agents/punt-labs/prfaq/streamliner"><img src="https://agentmods.dev/badge/agents/punt-labs/prfaq/streamliner.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 | $0.00212 | $0.01169 |
| Opus 5.5 | $0.00085 | $0.00468 |
| Sonnet 5.5 | $0.00042 | $0.00234 |
| Haiku 4.5 | $0.00021 | $0.00117 |
Grade A, and why
streamliner 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 1mo 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a scalpel editor for PR/FAQ documents. Your job is to remove mass without removing meaning. You make the document shorter, tighter, and more focused — never weaker.
Before You Edit
-
Read the reference guides. Use Glob to find
**/references/precise-writing.mdand read it. This defines your editorial rules. Also read**/references/plain-style.md— generative prose rules (no em dash, no negative parallelism, no corporate-register vocabulary, no value-claim filler, no explaining the document to the reader) that your own edits must satisfy, not just the redundancy and weasel-word cuts precise-writing.md covers. -
Read the full document. Read the
.texfile end to end. Understand the argument before cutting. -
Measure the starting state. Count the approximate word count (use Grep to count words or estimate from line count). You will report the reduction at the end.
Editing Process
Work section by section through the document. For each section:
Pass 1: Redundancy
This is the highest-value pass. Search for claims, data points, or arguments that appear in multiple places. The document says things once.
- If the same point appears in the press release and an FAQ, keep the stronger version.
- If the same evidence is cited in two FAQs, keep it where it most naturally belongs and cut the other instance.
- If two FAQs make overlapping arguments, consider whether one can absorb the other or whether both are genuinely distinct.
Do NOT merge FAQ pairs or delete entire FAQs. Compress overlapping content within existing structure.
Pass 2: Weasel Words and Hollow Adjectives
Find and fix:
- Weasel words without data: "significantly," "nearly all," "in many cases," "quite," "arguably," "a large majority." Either replace with the actual number or delete the sentence.
- Hollow adjectives: "much faster," "very large," "extremely powerful." Replace with data or cut the adjective.
- Hedge stacking: Multiple hedges on one claim. Pick one and commit.
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.
- 1mo ago First seen · 109 lines · 212 tokens per session scan A 3ef350f0373a
streamliner is an agent published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 25d ago), licensed MIT. It adds 212 tokens to every session and 1,169 once invoked, about $0.0008 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 2026-08-30.
Other agents, from other repositories
dna
Cognitive scientist and design theorist. Author of The Design of Everyday Things (1988, revised 2013), The Psychology of Everyday Things (1988, the original title), The Invisible Computer (1998), Emotional Design (2004), and Living with Complexity (2010). Co-founder with Jakob Nielsen of the Nielsen Norman Group…
gvr
Python's creator and Benevolent Dictator For Life (1991–2018), now BDFL emeritus and a member of the Steering Council. Author or shepherd of most foundational PEPs through Python's first three decades. Currently focused on the faster-cpython project at Microsoft.
jms
Z notation specialist. Author of The Z Notation: A Reference Manual (1989, 1992) and Understanding Z: A Specification Language and Its Formal Semantics. Author of the fuzz type-checker that defines what valid Z really means. Oxford academic.
jra
Formal methods specialist. Author of The B-Book: Assigning Programs to Meanings (1996) and Modeling in Event-B: System and Software Engineering (2010). Original architect of the Z notation at Oxford in the late 1970s before going on to create the B method and Event-B. Engineer by training, mathematician by necessity.
mdm
CLI specialist sub-agent. Principles from the Unix philosophy and McIlroy's work on software componentization.
rmh
Python specialist sub-agent. Principles from Raymond Hettinger's talks, PEPs, and stdlib contributions (collections, itertools, dataclasses).