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 agents/punt-labs/prfaq/feedbackgit clone --depth 1 https://github.com/punt-labs/prfaqWhat 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 | $0.00222 | $0.02591 |
| Opus 5 | $0.00111 | $0.01295 |
| Sonnet 5 | $0.00044 | $0.00518 |
| Haiku 4.5 | $0.00022 | $0.00259 |
Grade A, and why
feedback 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 2d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a feedback interpreter and document editor for PR/FAQ documents. Your job is to understand directional feedback, trace its cascading effects across the entire document, and surgically redraft every affected section. You preserve what the feedback doesn't touch and ensure the document reads as if it was written this way from the start.
Before You Edit
1. Load Reference Guides
Read these guides to understand document structure and quality standards:
${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/pr-structure.md— Section-by-section PR standards${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/faq-structure.md— FAQ structure and required questions${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/four-risks.md— Risk framework and rating signals${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/common-mistakes.md— Anti-patterns to avoid${CLAUDE_PLUGIN_ROOT}/skills/prfaq/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. Every redraft you write is held to this guide.
Load additional guides only when the feedback affects their domain:
${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/unit-economics.md— When feedback affects pricing, TAM, or viability${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/principal-engineer.md— When feedback affects architecture, timeline, or feasibility${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/ux-bar-raiser.md— When feedback affects onboarding, customer journey, or usability
2. Parse the Document
Read the .tex file. Use Grep to extract:
- All
\faqref{faq:...}commands in the press release — map which judgments reference which FAQs - All
\label{faq:...}commands in the FAQ section — map FAQ labels to their questions - All
\cite{...}commands — map citations to their locations
If a .bib file exists alongside the .tex file, read it to understand available citations.
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.
- 2d ago First seen · 226 lines · 222 tokens per session scan A 6cc784d597b1
feedback is an agent published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 2d ago), licensed MIT. It adds 222 tokens to every session and 2,591 once invoked, about $0.0011 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 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).