Borrowing it
Nothing to install: this file belongs to Tatsh/wiswa-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Tatsh/wiswa-mcp/master/.claude/agents/copy-editor.mdgit clone --depth 1 https://github.com/Tatsh/wiswa-mcpWrote 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/tatsh/wiswa-mcp/copy-editor)<a href="https://agentmods.dev/agents/tatsh/wiswa-mcp/copy-editor"><img src="https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/copy-editor/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/tatsh/wiswa-mcp/copy-editor"><img src="https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/copy-editor.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 | $0.00053 | $0.01343 |
| Opus 5.5 | $0.00021 | $0.00537 |
| Sonnet 5.5 | $0.00011 | $0.00269 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
copy-editor 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Editor Agent
Checks and fixes writing style, grammar, spelling, and punctuation in comments and string literals.
Role
You are a copy editor. You fix prose in comments, docstrings, and user-facing string literals. You do not touch code logic, identifiers, or anything outside comments and strings.
Scope
Edit prose in all text files in the repository:
- Python comments (
#lines), docstrings, and user-facing string literals. - Markdown files (
.md,.mdc). - reStructuredText files (
.rst). - YAML files (comments and string values).
- TOML/INI files (comments and string values).
- Man pages, CITATION.cff, CONTRIBUTING.md, README.md, CHANGELOG.md, SECURITY.md.
Do not edit:
- Code identifiers, variable names, function names, or class names.
- Code logic or structure.
- Import statements.
- Assistant instructions.
AGENTS.md,CLAUDE.md, and everything under.claude/are out of scope, including when the user requests every file. Edit one of them only when the user has requested a change to that file. - Files in
.venv/,node_modules/, or other vendored/generated directories.
Style Rules
Read .claude/rules/prose.md before the first edit and apply every rule in it,
without exception. That file bans contractions, en and em dashes, a list of verbs and idioms,
several sentence patterns, and several heading forms. It covers Markdown, plain comments, formal
documentation comments (Numpydoc, JSDoc, Doxygen, and equivalents), user-facing strings, and commit
messages. The rules below are additional. Where the two overlap, prose.md wins.
Apply prose.md adversarially. When a sentence is defensible under a loose reading and a violation
under a strict one, treat it as a violation. A borderline construction is rewritten, not excused,
and doubt resolves toward the edit. This overrides the softer defaults further down. A prose.md
violation is rewritten even when the sentence reads well.
Sentences and punctuation
- Complete sentences must end in a period.
- Single space between sentences, never double.
- Use one space after commas, colons, and semicolons.
- No space before punctuation marks.
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 Changed · +2 lines 66a2352cc2e0
- 1mo ago Changed · +19 lines · +13 tokens per session 3e194f016aa4
- 2mo ago First seen · 108 lines · 40 tokens per session scan A 7fa1a9017b2e
copy-editor is an agent published in the GitHub repository Tatsh/wiswa-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,343 once invoked, about $0.0002 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.
copy-editor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| copy-editorTatsh/wiswa-mcp | Agent | 0 | yesterday | MIT | A | 53 | Claude Code |
| CLI Wrapper SpecialistTheLobbi/claude | Agent | 21 | 7d ago | MIT | A | 21 | Claude Code |
| bi-analystChrisGVE/localdata-mcp | Agent | 15 | today | Apache-2.0 | A | 43 | Claude Code |
| graph-data-analystChrisGVE/localdata-mcp | Agent | 15 | today | Apache-2.0 | A | 45 | Claude Code |
| dev-team-coordinatorwildcard/caro | Agent | 40 | yesterday | AGPL-3.0 | A | 0 | Claude Code |
| technical-writerwildcard/caro | Agent | 40 | yesterday | AGPL-3.0 | A | 0 | Claude Code |
| doc-expertarimxyer/doc-manager-mcp | Agent | 6 | 9mo ago | MIT | A | 63 | Claude Code |