What is secret-guard?

Instructions for using redacted secret placeholders such as {{S_xxxxxxxx}} instead of exposing real credentials in prompts and files. The associated tool replaces a placeholder with the real value when a command runs.

Use it when placing a redacted credential in a .env file, an export command, a request header, or another configuration file.

It provides a consistent way to handle API keys, tokens, and passwords without asking for the real value again. It also explains where a credential must be stored for later sessions.

secret-guard — Skill for Claude Code by kimsb2429/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 kimsb2429/claude-skills --skill secret-guard

Clone the repo

git clone --depth 1 https://github.com/kimsb2429/claude-skills

Made for: Claude Code.

Or install secret-guard, the plugin that ships this one along with the rest of its 1 skill.

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/kimsb2429/claude-skills/secret-guard/github.svg)](https://agentmods.dev/skills/kimsb2429/claude-skills/secret-guard)

Your own site

<a href="https://agentmods.dev/skills/kimsb2429/claude-skills/secret-guard"><img src="https://agentmods.dev/badge/skills/kimsb2429/claude-skills/secret-guard/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/kimsb2429/claude-skills/secret-guard"><img src="https://agentmods.dev/badge/skills/kimsb2429/claude-skills/secret-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 323 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.00323
Opus 5.5	$0.00022	$0.00129
Sonnet 5.5	$0.00011	$0.00065
Haiku 4.5	$0.00006	$0.00032

Measured 2mo ago against content hash e4ee06c4133d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

secret-guard scanned grade A with 1 finding 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 3 executable files (.claude/types/claude-code-mcp.d.ts, .claude/types/claude-code.d.ts, hooks/secret-guard.ts), 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Use the placeholder verbatim wherever the real value belongs: `.env` lines, `export` statements, `curl -H` headers, config files. The secret-guard plugin swaps in the real value when the tool runs.

secret-guard/SKILL.md · 15 lines

What it actually says

secret-guard placeholders

A token shaped {{S_xxxxxxxx}} is a redacted credential. The real value never enters this conversation. The plugin holds it in memory for this session; once written to a .env file in the project it also resolves in later sessions (the id is a hash of the value).

Rules:

Use the placeholder verbatim wherever the real value belongs: .env lines, export statements, curl -H headers, config files. The secret-guard plugin swaps in the real value when the tool runs.
Never ask the user to paste the secret again. Never try to read it via cat, env, or any other route; tool output is scrubbed and will only show the placeholder.
When placing a key, prefer .env in the project root (create it if missing, add it to .gitignore), keyed by the provider name the placeholder context gives (e.g. ANTHROPIC_API_KEY).
A placeholder from a past session resolves only if the value sits in .env, .env.local, .env.development, .env.production, or .env.test in the working directory. If substitution fails, tell the user the key must be pasted again.

Files

What ships with it

9 files 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.

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 · 15 lines · 56 tokens per session scan A e4ee06c4133d

Subscribe to this mod's changes

secret-guard is a skill published in the GitHub repository kimsb2429/claude-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 323 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.