agentmods.dev

rewrite

rewrite is a skill for Claude Code, Codex from wiber/thetacog-mcp. It costs 112 tokens per session (654 once invoked), scanned A, original, MIT.

A file-editing review that finds unclear, padded, or hard-to-read sentences and suggests replacements. It can use a local or cloud writing model, but changes are only applied after the user chooses them.

In plain words
What is it for?
Use it to improve a draft, message, introduction, or other single file, especially when you want a report before making edits.
Why use it?
It helps locate wording that makes a document difficult to understand without silently rewriting the file.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 1repo yesterday A scan 112 tokens original MIT

Good fit Use it to improve a draft, message, introduction, or other single file, especially when you want a report before making edits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wiber/thetacog-mcp/rewrite
View source ↗ wiber/thetacog-mcp thetadriven.com
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.

Any agent
npx skills add wiber/thetacog-mcp --skill rewrite
Clone the repo
git clone --depth 1 https://github.com/wiber/thetacog-mcp

Made for: Claude Code, Codex.

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 rewrite

README.md
[![agentmods](https://agentmods.dev/badge/skills/wiber/thetacog-mcp/rewrite/github.svg)](https://agentmods.dev/skills/wiber/thetacog-mcp/rewrite)
Your own site
<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/rewrite"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/rewrite/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 rewrite

Your own site · 80×15
<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/rewrite"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/rewrite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 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 $0.00112 $0.00654
Opus 5.5 $0.00045 $0.00262
Sonnet 5.5 $0.00022 $0.00131
Haiku 4.5 $0.00011 $0.00065

Measured yesterday against content hash 1553301c7e92, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rewrite 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 yesterday.

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.

skills/rewrite/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rewrite — the anti-slop pass

Every command here is a door: npx thetacog-mcp <door>, run from the root of the repo you are working in. Nothing names a path on one machine.

On invocation

  1. Resolve the target to one existing file. When the user named none, use the file they are editing or the draft just written. Ask only when two files fit equally.
  2. Run the dry-run pass:
npx thetacog-mcp rewrite --file <path> --tracks C,D --limit 10
  • --tracks C,D uses the cloud writer (claude -p, the same login /steer uses). Tracks A and B are the local writer and need ollama with qwen2.5:7b; add them only when ollama list shows that model.
  • --from L120 or --from 40% or --from "<phrase>" starts the scan partway into a long file.
  • --limit N caps the cold sentences worked (default 15). Short, high-stakes text (a message, an intro) is where it pays most.
  1. The report lands in .thetacog/rewrite/reports/<file>-<stamp>.html. Open it (open <report> on macOS) and read the top card per cold sentence back to the user: the sentence, the winning candidate, and what it removed.
  2. Apply a candidate only when the user picks it. Edit the file yourself with the chosen line and commit it as one change. --apply commits every top candidate unattended; never pass it unless the user asks for exactly that.

What the report is sufficient for, and what it is not

  • Sufficient for: where a reader's comprehension broke, which lines carry hedges, filler or narrator-voice meta, and whether a candidate removed slop without adding words. The slop score is a pattern match a person can read and re-run to the same number.
  • Not sufficient for: whether the text is true, or whether the rewrite keeps the author's meaning. Check each picked line against the original before it lands.

When it cannot run

  • claude not on PATH: say so and stop. The cloud tracks are the writer.
  • A file with no prose paragraphs (code, JSON) reports zero cards. Say that it holds no prose; do not widen the scan.

Read the full file on GitHub · 41 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. yesterday First seen · 41 lines · 112 tokens per session scan A 1553301c7e92

Subscribe to this mod's changes

rewrite is a skill published in the GitHub repository wiber/thetacog-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 654 once invoked, about $0.0004 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 2026-11-06.

AI SafetyLLMWriting and docsagenticdeterminisminsurancemcp
Related

rewrite compared with skills from other repositories

rewrite next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rewritewiber/thetacog-mcpSkill1yesterdayMITA112Claude Code, Codex
git-checkpointagentscope-ai/agentscope-javaSkill6.3ktodayApache-2.0A39Claude Code, Codex
synthesize-reportagentscope-ai/agentscope-javaSkill6.3ktodayApache-2.0A29Claude Code, Codex
data-analysisagentscope-ai/agentscope-javaSkill6.3ktodayApache-2.0A25Claude Code, Codex
summarizeragentscope-ai/agentscope-javaSkill6.3ktodayApache-2.0A24Claude Code, Codex
agent-browserTencent/WeKnoraSkill37k4d agononeA83Claude Code, Codex
skill-creator-primersammcj/agentic-codingSkill1693d agoApache-2.0A74Claude Code