A local, statistics-only scan of a folder of session transcripts for personally identifying information. It reports counts and rates without showing the detected names, emails, or other private values.

Use it to audit a collection of sessions, compare redaction rates, see which kinds of private information occur, and estimate how much information remains undetected.

It lets you measure privacy risk across many transcripts without sending their contents to a cloud service. The report also avoids exposing filenames and transcript text.

audit — Skill 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.

Any agent

npx skills add glebis/claude-skills --skill audit

Clone the repo

git clone --depth 1 https://github.com/glebis/claude-skills

Made for: Claude Code.

Or install confide, the plugin that ships this one along with the rest of its 8 skills.

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/skills/glebis/claude-skills/audit/github.svg)](https://agentmods.dev/skills/glebis/claude-skills/audit)

Your own site

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

Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 912 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00184	$0.00912
Opus 5.5	$0.00074	$0.00365
Sonnet 5.5	$0.00037	$0.00182
Haiku 4.5	$0.00018	$0.00091

Measured 2mo ago against content hash 391764927e11, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/audit/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

confide:audit — corpus-scale, stats-only PII audit

Measure how much PII lives across a whole folder of sessions, without ever exposing any of it. The audit runs the layered LOCAL detector stack from shared/confide_core.py (regex → Natasha → local LLM) over each file and emits only aggregates. This mirrors the real_session_eval privacy contract: read text only in-process, emit counts.

Privacy invariants (do not violate)

Local-only. No cloud APIs. Raw transcript text never leaves the machine.
Stats-only output. The report (markdown + json + optional HTML) contains ONLY counts and rates — never a transcript substring, never a detected PII value.
No filenames. Per-file rows are keyed by anonymized ids own-00, own-01, … The original path/name is never written or printed. On an unreadable file, only the index + exception class name is recorded.
Safe to surface. Because it is counts-only, the aggregate report can be shared with a cloud agent or pasted into a chat. The PII stays on the machine.

What it reports

n_files, total / mean / min / max document chars
spans_by_type (PERSON, EMAIL, PHONE, DATE, …) and spans_by_layer (regex / natasha / llm)
overall_redaction_rate plus the per-session redaction-rate distribution (min / median / mean / max)
a coarse residual proxy: spans still detectable after redaction — ~0 on a clean RED corpus, a leakage signal on a GREEN corpus.

Run it

Point it at a folder (recurses, processes every .md/.txt; skips confide's own *.green.md / *.stats.json outputs):

python3 skills/audit/scripts/audit.py FOLDER

Options:

--list paths.txt — also/instead audit absolute paths listed one per line.
--layers regex,natasha,llm — choose detection layers (default from config). Use --layers regex for a fully offline, deterministic pass (no models/network).
--out report.md — report path; a report.json sibling is written alongside.
--html — also write a Tufte-ish dashboard (report.html, counts only).

Read the full file on GitHub · 63 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/audit.py 17 KB runs code

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 · 63 lines · 184 tokens per session scan A 391764927e11

Subscribe to this mod's changes

audit is a skill published in the GitHub repository glebis/claude-skills (409 stars, last pushed yesterday), licensed MIT. It adds 184 tokens to every session and 912 once invoked, about $0.0007 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 2026-08-30.

Security agent-skills claude-skills codex-skill

audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
auditglebis/claude-skills	Skill	409	yesterday	MIT	A	184	Claude Code
tastemakercodeswithroh/tastemaker	Skill	524	26d ago	MIT	A	202	Claude Code
fdesuboss87/FDEOps	Skill	857	17d ago	MIT	A	125	Claude Code, Codex
board-memosuboss87/FDEOps	Skill	857	17d ago	MIT	A	31	Claude Code, Codex
briefsuboss87/FDEOps	Skill	857	17d ago	MIT	A	32	Claude Code, Codex
business-casesuboss87/FDEOps	Skill	857	17d ago	MIT	A	29	Claude Code, Codex
earn-trustsuboss87/FDEOps	Skill	857	17d ago	MIT	A	26	Claude Code, Codex