Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
A skill your agent uses when the user asks to purge anthropies, strip Co-Authored-By Claude, strip Generated-with banners, inspect owned files for vendor marks, clean hard-bound C2PA metadata from…
Install Purge Anthropies
$ npx skills add CharlesHoskinson/anthropies --skill purge-anthropies -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CharlesHoskinson/anthropies purge-anthropies --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/CharlesHoskinson/anthropies.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/purge-anthropies .claude/skills/purge-anthropies && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "purge-anthropies" agent skill from https://github.com/CharlesHoskinson/anthropies/tree/main/skills/purge-anthropies into .claude/skills/purge-anthropies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "purge-anthropies", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/CharlesHoskinson/anthropies/tree/main/skills/purge-anthropiesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add CharlesHoskinson/anthropies --skill purge-anthropies -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CharlesHoskinson/anthropies purge-anthropies --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CharlesHoskinson/anthropies.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/purge-anthropies .agents/skills/purge-anthropies && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "purge-anthropies" agent skill from https://github.com/CharlesHoskinson/anthropies/tree/main/skills/purge-anthropies into .agents/skills/purge-anthropies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "purge-anthropies", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CharlesHoskinson/anthropies --skill purge-anthropies -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CharlesHoskinson/anthropies purge-anthropies --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CharlesHoskinson/anthropies.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/purge-anthropies .cursor/skills/purge-anthropies && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "purge-anthropies" agent skill from https://github.com/CharlesHoskinson/anthropies/tree/main/skills/purge-anthropies into .cursor/skills/purge-anthropies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "purge-anthropies", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/CharlesHoskinson/anthropies.git --path skills/purge-anthropies--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add CharlesHoskinson/anthropies --skill purge-anthropies -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CharlesHoskinson/anthropies purge-anthropies --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CharlesHoskinson/anthropies.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/purge-anthropies .gemini/skills/purge-anthropies && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "purge-anthropies" agent skill from https://github.com/CharlesHoskinson/anthropies/tree/main/skills/purge-anthropies into .gemini/skills/purge-anthropies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "purge-anthropies", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install CharlesHoskinson/anthropies purge-anthropiesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add CharlesHoskinson/anthropies --skill purge-anthropies -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CharlesHoskinson/anthropies.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/purge-anthropies .github/skills/purge-anthropies && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "purge-anthropies" agent skill from https://github.com/CharlesHoskinson/anthropies/tree/main/skills/purge-anthropies into .github/skills/purge-anthropies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "purge-anthropies", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CharlesHoskinson/anthropies --skill purge-anthropies -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CharlesHoskinson/anthropies purge-anthropies --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CharlesHoskinson/anthropies.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/purge-anthropies .opencode/skills/purge-anthropies && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "purge-anthropies" agent skill from https://github.com/CharlesHoskinson/anthropies/tree/main/skills/purge-anthropies into .opencode/skills/purge-anthropies/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "purge-anthropies", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
purge-anthropies- GitHub stars
- 192
- Token cost
- ~1.3k tokens
- SKILL.md length
- 520 words
- Files
- 2 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when the user asks to purge anthropies, strip Co-Authored-By Claude, strip Generated-with banners, inspect owned files for vendor marks, clean hard-bound C2PA metadata from…
- Works in 2 steps: Resolve the target: path, selection, or… → Prefer the local HTTP service for…
- The user asks to purge anthropies
- SKILL.md covers Hard rules, Procedure, Do not and Additional resources
- Calls npx, curl and node; needs ANTHROPIES_SERVER_API_KEY
What it does
Purge Anthropies is an agent skill from CharlesHoskinson/anthropies. Use when the user asks to purge anthropies, strip Co-Authored-By Claude, strip Generated-with banners, inspect owned files for vendor marks, clean hard-bound C2PA metadata from owned png/jpg/svg (and other supported files), or runs /purge-anthropies or /anthropies. Does not claim official watermark removal.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/mark.md`).
It sits in Development. The repository describes itself as: Restore clean title in work you already own. Strip vendor marks from Outputs Anthropic assigned to you. The licence is Apache-2.0.
When your agent uses it
- The user asks to purge anthropies
- Strip Co-Authored-By Claude
- Strip Generated-with banners
- Inspect owned files for vendor marks
Example prompts
- “/purge-anthropies”
Requirements
- Node.js
- A credential in ANTHROPIES_SERVER_API_KEY
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Resolve the target: path, selection, or commit message the user named.
- Prefer the local HTTP service for inspect/clean.
What it can do on your machine
Read from SKILL.md and the folder at commit 6b60854. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
npxcurlnodepnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, curl and pnpm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
ANTHROPIES_SERVER_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Purge Anthropies loads about 1.3k tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 81 tokens; SKILL.md has 520 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from CharlesHoskinson/anthropies at commit 6b60854, republished under its Apache-2.0 licence (© CharlesHoskinson). 520 words, ~1,274 tokens.
Download SKILL.mdSave it as
.claude/skills/purge-anthropies/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- purge-anthropies
- description
- Use when the user asks to purge anthropies, strip Co-Authored-By Claude, strip Generated-with banners, inspect owned files for vendor marks, clean hard-bound C2PA metadata from owned png/jpg/svg (and other supported files), or runs /purge-anthropies or /anthropies. Does not claim official watermark removal.
Purge Anthropies
Restore clean title in Outputs the user already owns. The Claude text mark is a SynthID-class keyed sampler. It is the wording. Hidden-character strip does not touch it.
humanize is title restoration: a best-effort wording rewrite on a non-origin model. Residual statistical risk remains. print-prompt does not destamp. This is not an official-kill.
Hard rules
- Do not rewrite with Claude, Gemini, or any origin/watermarked vendor. That re-stamps the mark.
- Do not claim official-detector failure. There is no public Claude detector.
- Do not synonym-swap in place. That leaves H-grams intact.
- Deterministic clean first. Humanize second.
Procedure
Resolve the target: path, selection, or commit message the user named.
Prefer the local HTTP service for inspect/clean.
ANTHROPIES_SERVICE_URL defaults to http://127.0.0.1:8765. The process that owns FileSystem is anthropies serve (loopback 127.0.0.1:8765 unless the operator passed --host / --port):
npx anthropies serveFrom this repo after pnpm build: node dist/cli.js serve.
Health-check first:
: "${ANTHROPIES_SERVICE_URL:=http://127.0.0.1:8765}"
curl -sS -f "$ANTHROPIES_SERVICE_URL/health"Expected: {"ok":true,"version":"0.3.0"}. If health fails, say so. Do not invent a successful HTTP result. If the operator required the service, stop and report the failure. Otherwise use the local CLI fallback:
npx anthropies clean --in-place <path>If the package is not installed, run it from the repo after pnpm build: node dist/cli.js clean --in-place <path>.
When health succeeds, POST base64. If ANTHROPIES_SERVER_API_KEY is set, add -H "Authorization: Bearer $ANTHROPIES_SERVER_API_KEY":
file_b64=$(base64 < <path> | tr -d '\n')
name=$(basename <path>)
# inspect → { ok, kind, report }
curl -sS -X POST "$ANTHROPIES_SERVICE_URL/inspect" \
-H "Content-Type: application/json" \
-d "{\"file\":\"$file_b64\",\"name\":\"$name\"}"
# clean → { ok, kind, report, cleaned } (cleaned is base64; Layer A / hard-bound metadata only)
curl -sS -X POST "$ANTHROPIES_SERVICE_URL/clean" \
-H "Content-Type: application/json" \
-d "{\"file\":\"$file_b64\",\"name\":\"$name\"}"There is no HTTP /humanize. Official stays unavailable unless ANTHROPIC_DETECT_URL is set. This run does not prove the official Claude text detector will fail.
Classify the file.
- Commit message / PR body: stop after clean. Trailers and banners are the mark.
- Code: humanize comments, docstrings, and free strings only. Do not rename public APIs. Do not rewrite lockfiles, generated stubs, or snapshots.
- Prose / markdown: humanize the prose outside fences. Leave fenced code, tables of facts, URLs, and citations.
Humanize without the origin model. Humanize is CLI-only.
If the current host is Claude or Gemini, do not rewrite in this session. Run:
Show full SKILL.md (206 more words)Show less
ANTHROPIES_REWRITE_BACKEND=print-prompt npx anthropies humanize <path>print-prompt prints a rewrite prompt. It does not destamp. Then execute that prompt on a local unmarked model (Ollama / local Llama / Qwen / Mistral / DeepSeek with watermarking off). Optional:
ANTHROPIES_REWRITE_BACKEND=ollama ANTHROPIES_REWRITE_MODEL=llama3.2 npx anthropies humanize --in-place <path>If the current host is already unmarked (Grok, local open-weight, etc.), rewrite in-session:
- Change clause order, sentence boundaries, discourse markers, and function words.
- Target well under 50% surviving 5-grams.
- Keep facts, numbers, names, URLs, and code fences.
- For code, rewrite comment wording only unless the user opted into local-identifier rename.
- Report to the user:
- what deterministic marks were removed
- whether inspect/clean ran over HTTP (
ANTHROPIES_SERVICE_URL) or the local CLI fallback - whether a rewrite ran, and on which backend
- residual risk: statistical marks may remain; title restoration is best-effort; this is not an official-detector certificate and not an official-kill
Do not
| Move | Why |
|---|---|
| Ask Claude to "make this unmarked" | Re-stamps the same keyed sampler |
| Light copy-edit / prettier-only | H-gram islands survive |
Touch lockfiles, go.sum, protobufs | No free tokens; high breakage |
| Patch Claude Code request apostrophes | Different problem (outbound client steg) |
| Claim official-detector failure | Official stays unavailable unless a URL is set |
Additional resources
references/mark.md— how the mark works- Start the service:
npx anthropies serve(defaulthttp://127.0.0.1:8765) - Discover routes:
GET $ANTHROPIES_SERVICE_URL/openapi.json - Repo CLI:
npx anthropies --helpornode dist/cli.js --help
© CharlesHoskinson, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in skills/purge-anthropies of CharlesHoskinson/anthropies.
- SKILL.md
- references/mark.md
Open the folder on GitHubat commit 6b60854
Compare with similar skills
Purge Anthropies next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Purge Anthropies this skillCharlesHoskinson/anthropies | 192 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 4 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
Related
Categories
Questions about Purge Anthropies
What does Purge Anthropies do?
A skill your agent uses when the user asks to purge anthropies, strip Co-Authored-By Claude, strip Generated-with banners, inspect owned files for vendor marks, clean hard-bound C2PA metadata from…. Purge Anthropies is an agent skill from CharlesHoskinson/anthropies. Use when the user asks to purge anthropies, strip Co-Authored-By Claude, strip Generated-with banners, inspect owned files for vendor marks, clean hard-bound C2PA metadata from owned png/jpg/svg (and other supported files), or runs /purge-anthropies or /anthropies.
When should I use Purge Anthropies?
Purge Anthropies fits situations like: the user asks to purge anthropies; strip Co-Authored-By Claude; strip Generated-with banners; inspect owned files for vendor marks.
How do I install Purge Anthropies in Claude Code?
Run `npx skills add CharlesHoskinson/anthropies --skill purge-anthropies -a claude-code`. Or copy the skill folder (skills/purge-anthropies in CharlesHoskinson/anthropies) into .claude/skills/purge-anthropies in your project. Claude Code loads it when a task matches its description.
How do I install Purge Anthropies in Codex?
Run `npx skills add CharlesHoskinson/anthropies --skill purge-anthropies -a codex`. Or copy the skill folder (skills/purge-anthropies in CharlesHoskinson/anthropies) into .agents/skills/purge-anthropies in your project. Codex loads it when a task matches its description.
Can I use Purge Anthropies in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CharlesHoskinson/anthropies --skill purge-anthropies -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/purge-anthropies, .gemini/skills/purge-anthropies, .github/skills/purge-anthropies and .opencode/skills/purge-anthropies in your project.
What does Purge Anthropies need to run?
Going by SKILL.md and its folder, Purge Anthropies needs the command-line tools its instructions call (npx, curl, node and pnpm) and credentials named ANTHROPIES_SERVER_API_KEY. Our summary lists: Node.js; A credential in ANTHROPIES_SERVER_API_KEY.
Does Purge Anthropies access the network?
SKILL.md contains no URLs. Its commands use npx and curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Purge Anthropies safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Purge Anthropies use?
Purge Anthropies is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Purge Anthropies use?
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 181 tokens, read only when the agent opens those files.
What are the alternatives to Purge Anthropies?
Skills that share tags, products or a category with Purge Anthropies: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Purge Anthropies?
CharlesHoskinson (a GitHub user) maintains it in CharlesHoskinson/anthropies, which has 192 GitHub stars. The repository was last updated on August 24, 2026.
Source: CharlesHoskinson/anthropies on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.