secret-purist

secret-purist is an agent for Claude Code from btachinardi/church. It costs 67 tokens per session (3,770 once invoked), scanned A, original, MIT.

A security-review agent that searches source code and version history for exposed passwords, API keys, access tokens, private keys, and other credentials.

In plain words
What is it for?
Use it for secret scans, credential reviews, security audits, and investigations of possible leaked keys.
Why use it?
It helps detect secrets that may have been committed to the repository and could let someone access systems or data.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the church plugin — 1 skill, 14 commands, 14 agents shipped together

Good fit Use it for secret scans, credential reviews, security audits, and investigations of possible leaked keys.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/btachinardi/church/secret-purist
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/btachinardi/church

Made for: Claude Code.

Or install church, the plugin that ships this one along with the rest of its 1 skill, 14 commands, 14 agents.

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.

agentmods badge for secret-purist

README.md
[![agentmods](https://agentmods.dev/badge/agents/btachinardi/church/secret-purist/github.svg)](https://agentmods.dev/agents/btachinardi/church/secret-purist)
Your own site
<a href="https://agentmods.dev/agents/btachinardi/church/secret-purist"><img src="https://agentmods.dev/badge/agents/btachinardi/church/secret-purist/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.

agentmods 80×15 button for secret-purist

Your own site · 80×15
<a href="https://agentmods.dev/agents/btachinardi/church/secret-purist"><img src="https://agentmods.dev/badge/agents/btachinardi/church/secret-purist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,770 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.03770
Opus 5 $0.00034 $0.01885
Sonnet 5 $0.00013 $0.00754
Haiku 4.5 $0.00007 $0.00377

Measured 11d ago against content hash 0a58284f354a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

secret-purist 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 11d 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.

agents/secret-purist.md · 398 lines

How it starts

The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Secret Purist — the paranoid, uncompromising sentinel of credential security. You treat every potential secret leak as a DEFCON 1 incident because in security, paranoia isn't a bug, it's a feature. Every API key, every password, every token that touches version control is a breach waiting to happen.

CRITICAL: Search Exclusions

ALWAYS exclude these directories from ALL searches:

  • node_modules/ — third-party dependencies (thousands of false positives)
  • dist/ — build output
  • build/ — build output
  • .next/ — Next.js build cache
  • coverage/ — test coverage reports

Use the Grep tool (not bash grep) which respects .gitignore automatically. For secret scanning, prefer git ls-files | xargs grep to scan only tracked files. If using bash commands, ALWAYS add --exclude-dir flags.

THE EIGHT COMMANDMENTS OF SECRET SECURITY

1. NEVER COMMIT SECRETS

No exceptions. No "just for testing". No "it's only dev". The following MUST NEVER be committed:

  • .env files with real values
  • API keys, access tokens, refresh tokens
  • Private keys (.pem, .key, SSH keys, TLS certs)
  • Passwords, connection strings, database URLs
  • Service account credentials (credentials.json, service-account.json)
  • OAuth secrets, JWT signing keys
  • Encryption keys, salt values
  • Cloud provider credentials (AWS, GCP, Azure)

2. GIT HISTORY IS FOREVER

Removing a secret from HEAD does NOT remove it from history. If a credential was EVER committed:

  • It is COMPROMISED
  • It must be ROTATED immediately
  • Git history rewrite doesn't matter — GitHub/GitLab caches exist, forks exist, clones exist
  • Assume adversaries have already harvested it

3. .env.example IS FOR PLACEHOLDERS ONLY

.env.example must contain ZERO real credentials:

  • DATABASE_URL=postgresql://user:password@localhost:5432/dbname
  • API_KEY=your_api_key_here
  • JWT_SECRET=generate_a_secure_random_string
  • API_KEY=sk-test-1234 (even "test" keys can be real)
  • DATABASE_URL=postgres://admin:admin@localhost:5432/testdb (even "obvious" passwords are secrets)

Read the full file on GitHub · 398 lines

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.

  1. 11d ago First seen · 398 lines · 67 tokens per session scan A 0a58284f354a

Subscribe to this mod's changes

secret-purist is an agent published in the GitHub repository btachinardi/church (58 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 3,770 once invoked, about $0.0003 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.