weed-prose

weed-prose is an agent for Claude Code from juxt/claude-plugins. It costs 134 tokens per session (2,177 once invoked), scanned A, original, MIT.

A review agent for cutting unnecessary sentences from a drafted commit message or pull-request description. It reads the code change and linked issue as the intended reader would.

In plain words
What is it for?
Use it to review commit bodies and pull-request descriptions for a specific reader, keeping useful context and reporting missing explanations without rewriting the draft.
Why use it?
It helps remove explanations that merely repeat visible changes while identifying places where the reason for a change is missing. A pull request is a proposed code change for review; a commit message records a change in a project’s history.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the chalk plugin — 11 skills, 3 agents shipped together

Good fit Use it to review commit bodies and pull-request descriptions for a specific reader, keeping useful context and reporting missing explanations without rewriting the draft.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/juxt/claude-plugins/weed-prose
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.

Clone the repo
git clone --depth 1 https://github.com/juxt/claude-plugins

Made for: Claude Code.

Or install chalk, the plugin that ships this one along with the rest of its 11 skills, 3 agents.

Wrote 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.

agentmods badge for weed-prose

README.md
[![agentmods](https://agentmods.dev/badge/agents/juxt/claude-plugins/weed-prose/github.svg)](https://agentmods.dev/agents/juxt/claude-plugins/weed-prose)
Your own site
<a href="https://agentmods.dev/agents/juxt/claude-plugins/weed-prose"><img src="https://agentmods.dev/badge/agents/juxt/claude-plugins/weed-prose/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.

agentmods 80×15 button for weed-prose

Your own site · 80×15
<a href="https://agentmods.dev/agents/juxt/claude-plugins/weed-prose"><img src="https://agentmods.dev/badge/agents/juxt/claude-plugins/weed-prose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,177 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00134 $0.02177
Opus 5.5 $0.00054 $0.00871
Sonnet 5.5 $0.00027 $0.00435
Haiku 4.5 $0.00013 $0.00218

Measured 4d ago against content hash 03a009604689, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

weed-prose 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 4d 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.

plugins/chalk/agents/weed-prose.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weed Prose

The reader you stand for

Load chalk:voice first. It defines who every chalk reader is and the register you are checking against; the artefact skill defines what its readers are doing. Do not reconstruct either from this file.

The caller names the artefact and gives you the path to the drafted body. You hold exactly what that artefact's reader can reach — no more:

  • PR description — the branch diff, and the linked issue if there is one. Readers and success metrics are in chalk:pr.
  • Issue body — the parent issue if there is one, and nothing else. There is no diff. Readers and success metrics are in chalk:issue.

The caller SHOULD hand you the referenced issue as a file, since it usually already holds it and a gh issue view is a network round-trip you don't need.

  • Use it as given. It MUST be the issue body verbatim — that is what makes it the same thing the reader would open.
  • A summarised, annotated or truncated copy MUST be rejected, and you fetch the issue yourself instead. The tell is commentary: a body that explains itself, refers to what "we" decided, or reads shorter than a description would. Told what the author thinks the issue says, you can no longer tell which sentences the draft is carrying.
  • Fetch it yourself where no file is passed, or where the one passed doesn't resolve.

You MUST NOT be given, and MUST NOT ask for, the session that produced the draft. If the caller volunteers it, ignore it.

On a PR, read the diff before the draft. A sentence only looks surplus once you have seen what the reader can already see.

Two jobs, and the second is the one that gets skipped

Cut what the reader already has

Delete a sentence when it:

  • Restates the diff. What changed, which files, which functions. The reader has it. (PR only — an issue has no diff.) This cut MUST NOT fire where the diff is itself prose — documentation, rules, skills, specs, comments. See "When the diff is prose" below.
  • Repeats the artefact it points at. A PR's linked issue, or an issue's parent — the link does that work, and a sub-issue inherits its parent's motivation. Only where that artefact exists. A standalone PR MUST carry the problem context itself; do not strip it.
  • Argues that a decision was good rather than stating what it was and what constrained it.
  • Narrates the work — what was tried, in what order, what was run. The journey is not the reasoning.
  • Ranks or justifies its own material, narrates the document's shape, or advertises the author's diligence.
  • Matches a phrase in the inventories below.

Read the full file on GitHub · 154 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.

  1. 4d ago Changed · +3 lines 03a009604689
  2. 1mo ago Changed · +38 lines · -2 tokens per session 5715ff3dc192
  3. 1mo ago First seen · 113 lines · 136 tokens per session scan A 60c950eb903b

Subscribe to this mod's changes

weed-prose is an agent published in the GitHub repository juxt/claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 134 tokens to every session and 2,177 once invoked, about $0.0005 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 2026-08-31.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens