A command for applying written feedback to a PR/FAQ document, a document explaining a proposal and answering likely questions. It updates affected sections, recompiles the document, and checks the result.

Use it after review meetings or individual comments, including when feedback is provided directly or in a Markdown meeting summary.

It reduces the risk of changing one section while leaving related explanations inconsistent or outdated.

feedback — Command by punt-labs

Install

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.

agentmods

npx agentmods add commands/punt-labs/prfaq/feedback

Clone the repo

git clone --depth 1 https://github.com/punt-labs/prfaq

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,296 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00013	$0.01296
Opus 5	$0.00006	$0.00648
Sonnet 5	$0.00003	$0.00259
Haiku 4.5	$0.00001	$0.00130

Measured 2d ago against content hash 1d633b4c5703, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugin/commands/feedback.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incorporate Feedback into PR/FAQ

Interpret user feedback, trace cascading effects across all affected sections, redraft surgically, recompile, and validate with peer review. Supports single feedback or batch mode from meeting summary files.

Steps

Find the document. Search for prfaq.tex in the project root using Glob. If not found, ask the user for the path.
Determine mode. Three branches based on $ARGUMENTS:

a) Feedback text — $ARGUMENTS is non-empty and does NOT end in .md: treat it as literal feedback text (single mode). Skip step 3, proceed to step 4.

b) Explicit file path — $ARGUMENTS is a single file path ending in .md and the file exists: treat it as the meeting summary file path (batch mode). Proceed to step 3. If the file does not exist, treat $ARGUMENTS as feedback text (single mode, same as branch a).

c) Auto-discover — $ARGUMENTS is empty: search for meeting-summary-*.md and meeting-hive-summary-*.md in ./meetings/ first, then fall back to the project root (same directory as the .tex document) for un-migrated files. If one or more are found, show the most recent one's filename and ask the user via AskUserQuestion:
- Apply all directives from this file (batch mode — proceed to step 3, skip its confirmation)
- Enter feedback manually (single mode, ask for text, skip step 3, proceed to step 4)
- Cancel
If no meeting summary files are found, ask the user what feedback they want to apply (single mode — skip step 3, proceed to step 4).
Parse batch directives (batch mode only). Read the meeting summary file (from the path in step 2b or auto-discovered in step 2c) and extract directives from the ## Revision Queue (for /prfaq:feedback) section. Each directive is a ### Directive N: Title header followed by its body text.

If the user already chose "Apply all directives" in step 2c, skip confirmation and proceed to step 4. Otherwise, confirm with the user via AskUserQuestion:
- Apply all N directives
- Pick specific directives (show numbered list, let user choose)
- Cancel

Read the full file on GitHub · 71 lines

Changes

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 · 71 lines · 13 tokens per session scan A 1d633b4c5703

Subscribe to this mod's changes

feedback is a command published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 1,296 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 2026-08-30.

LaTeX Writing and docs beta claude-code-plugin pdf-generation product-discovery

feedback

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Incorporate Feedback into PR/FAQ

Steps

What this file has done since we first saw it

Other commands, from other repositories

oracle-dev

refine-dev

refine

contracts-dev

prove-dev

prove