A local toolkit for removing personally identifying information from session transcripts. It can redact details, check remaining identification risk, show changes, store encrypted data, and later restore the original values.

Anonymizing transcripts, reviewing redactions, checking privacy risks, scanning collections, and managing reversible mappings securely.

It helps you analyze or share transcripts without sending the raw personal details or the restoration map away from your computer.

confide — Plugin for Claude Code by glebis/claude-skills

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/glebis/claude-skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/glebis/claude-skills/confide/github.svg)](https://agentmods.dev/plugins/glebis/claude-skills/confide)

Your own site

<a href="https://agentmods.dev/plugins/glebis/claude-skills/confide"><img src="https://agentmods.dev/badge/plugins/glebis/claude-skills/confide/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/glebis/claude-skills/confide"><img src="https://agentmods.dev/badge/plugins/glebis/claude-skills/confide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 8 skills cost 1,007 tokens a session between them.

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.

Security

Grade A, and why

confide 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 2mo 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.

confide/.claude-plugin/plugin.json · 9 lines

What it actually says

{
  "name": "confide",
  "description": "CONFIDE — local-first de-identification toolkit for session transcripts. Skills: confide:setup (install deps + choose preferences), confide:anon (redact PII locally + emit a reversible map), confide:red (residual re-identification risk check), confide:rehydrate (restore real values into a cloud analysis locally), confide:view (interactive HTML redaction diff), confide:audit (stats-only corpus PII scan), confide:vault (three-locks encrypted storage), confide:annotate (gold set + inter-annotator agreement). Privacy-first; raw text and the reversible map never leave the machine.",
  "version": "0.2.0",
  "author": { "name": "Gleb Kalinin" },
  "repository": "https://github.com/glebis/claude-skills",
  "license": "MIT"
}

Contents

What it installs

The manifest is a name and a version. 8 skills travel with it, and installing the plugin installs all of them — 1,007 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

2mo ago First seen · 9 lines scan A f67a6f493d9a

Subscribe to this mod's changes

confide is a plugin published in the GitHub repository glebis/claude-skills (409 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Security agent-skills claude-skills codex-skill

confide next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
confideglebis/claude-skills	Plugin	409	yesterday	MIT	A	—	Claude Code
human-state-skillssoftcane/human-state-skills	Plugin	121	3mo ago	MIT	A	—	Claude Code
gitwiseJartan-LLC/grimoire	Plugin	3	4d ago	MIT	A	—	Claude Code
a-stock-skillsTaosheng777/BigA-stock-skills	Plugin	3	18d ago	MIT	A	—	Claude Code
requiems-api-skillsbobadilla-tech/requiems-api-skills	Plugin	2	yesterday	MIT	A	—	Claude Code
orientChaitanya299/Orient	Plugin	9	10d ago	none	A	—	Claude Code
cmtody-agent/codymaster	Plugin	56	2mo ago	none	A	—	Claude Code