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.
npx agentmods add instructions/fullstackcrew-alpha/privacy-mask/claude-mdgit clone --depth 1 https://github.com/fullstackcrew-alpha/privacy-maskWhat 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 | $0.00783 | $0.00783 |
| Opus 5 | $0.00392 | $0.00392 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
privacy-mask CLAUDE.md 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 3d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
privacy-mask
Local image privacy masking tool — detect and redact sensitive info via OCR + regex before images leave your machine.
Build & Test
pip install -e .
PYTEST_DISABLE_PLUGIN_AUTOLOAD=1 python -m pytest tests/ -v
Project Structure
mask_engine/— core library (OCR, detection, masking, CLI)mask_engine/data/config.json— 47 regex detection rules + masking/OCR settingstests/test_detector.py— detection rule tests (208+), each rule has positive and negative casesSKILL.md— agentskills.io standard skill definition.claude-plugin//hooks//scripts/— Claude Code plugin structure
GitHub Operations
This repo belongs to fullstackcrew-alpha. Before any gh command (push, PR, topics, releases, etc.), switch to the correct account:
gh auth switch -u fullstackcrew-alpha
Switch back after if needed: gh auth switch -u haowu77
PyPI Publish
PyPI 发布通过 GitHub Release 自动完成（CI workflow .github/workflows/publish.yml）：
gh auth switch -u fullstackcrew-alpha
gh release create v<version> --title "v<version> — 描述" --notes "changelog"
- Token 存在 GitHub repo secrets (
PYPI_API_TOKEN)，不需要本地凭证 - 不要用
twine upload本地发布，直接创建 Release 即可 - Release 会自动触发 build → check → publish 流程
ClawHub Publish
clawhub whoami # verify logged in as fullstackcrew-alpha
clawhub publish . --version <semver> --tags "privacy,pii,masking,redaction,security,ocr,screenshot,sensitive-data,data-protection,offline,local,claude-code,api-keys,secrets" --changelog "description"
--versionis required (valid semver)--tagsis critical for discoverability — ClawHub uses vector search, so without semantic tags the skill won't appear in search results.clawhubignorecontrols which files are included- SKILL.md frontmatter provides metadata
Version sync checklist
When bumping versions, update all four locations:
pyproject.tomlversionfieldmask_engine/__init__.py__version__SKILL.mdfrontmatterversionfieldmarketplace.jsonversionfield
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.
- 3d ago First seen · 74 lines · 783 tokens per session scan A 3288ac97d0f9
privacy-mask CLAUDE.md is an instructions file published in the GitHub repository fullstackcrew-alpha/privacy-mask (11 stars, last pushed 5mo ago), licensed MIT. It adds 783 tokens to every session, about $0.0039 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.
Other instructions, from other repositories
gate CLAUDE.md
Instructions for GaaraZhu/gate, covering gate, notes, repository structure, build and test commands and before every commit.
full-page-pdf-snap AGENTS.md
Instructions for Bubu89/full-page-pdf-snap, covering agents.md, worum es geht, wo du stehst, vor der ersten änderung and die regeln, die hier anders sind als üblich.
cloakbot AGENTS.md
AGENTS.md instructions for spire-studio/cloakbot, covering agent harness, operating contract, where to look, privacy first and verification.
cloakbot CLAUDE.md
Claude Code instructions for spire-studio/cloakbot, a project described as: A privacy-first AI agent that sanitizes your prompts locally with a local LLM before forwarding to remote LLM APIs.
stride-gpt AGENTS.md
Instructions for mrwadams/stride-gpt, covering agents.md, what this project is, repository layout, how the agentic analysis works and progressive disclosure pattern.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.