secrets-config-audit

secrets-config-audit is a skill for Claude Code, Codex from evolplus/talos. It costs 56 tokens per session (670 once invoked), scanned B, original, Apache-2.0.

A review of whether an application's environment settings and secrets are ready for deployment, without revealing secret values. Secrets include passwords, API keys, certificates, and cloud credentials.

In plain words
What is it for?
Use it to check required environment keys, secret-manager or CI/CD sources, credential-file presence, rotation notes, and redacted deployment evidence.
Why use it?
It finds missing settings, unsafe storage, unclear ownership, and broken injection paths before deployment.

Skill for Claude CodeCodex

Part of the talos plugin — 62 skills, 2 commands, 4 hooks shipped together

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.

agentmods
npx agentmods add skills/evolplus/talos/secrets-config-audit
Any agent
npx skills add evolplus/talos --skill secrets-config-audit
Clone the repo
git clone --depth 1 https://github.com/evolplus/talos

Made for: Claude Code, Codex.

Or install talos, the plugin that ships this one along with the rest of its 62 skills, 2 commands, 4 hooks.

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 secrets-config-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/evolplus/talos/secrets-config-audit.svg)](https://agentmods.dev/skills/evolplus/talos/secrets-config-audit)
Your own site
<a href="https://agentmods.dev/skills/evolplus/talos/secrets-config-audit"><img src="https://agentmods.dev/badge/skills/evolplus/talos/secrets-config-audit.svg" alt="Measured on agentmods" 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 670 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00056 $0.00670
Opus 5 $0.00028 $0.00335
Sonnet 5 $0.00011 $0.00134
Haiku 4.5 $0.00006 $0.00067

Measured 5d ago against content hash 989ac7388092, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

secrets-config-audit scanned grade B 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 5d 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.

Harvests environment variablesmediumData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

- Never run commands that dump credential material, including full `docker compose config`, `kubectl config view --raw`, `env`, or `printenv` on remote hosts.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/secrets-config-audit/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Secrets Config Audit

When to use

Use this skill before any deployment that depends on runtime configuration, secrets, environment files, registry credentials, cloud credentials, SSH, Kubernetes, or external service keys.

Inputs and outputs

  • Inputs: SRS environment contract, architecture config section, safe env templates, deploy mechanism, secret manager references, target environment, and required service integrations.
  • Outputs: redacted config readiness verdict, missing key names, unsafe storage findings, rotation/owner notes, and deploy-report config fields.

Procedure

  1. Collect declared keys. Read SRS/architecture config contracts and safe templates (.env.example, .env.template, .env.sample) for key names, owners, required environments, and secret classification.
  2. Detect secret-bearing files by status only. Check presence/path of .env*, .ssh/, .k8s/*config*, .docker/config.json, kubeconfigs, and credential files without reading contents.
  3. Verify injection path. Confirm each secret has a source: secret manager, Kubernetes Secret/ExternalSecret, CI/CD variable, operator-managed env file, or documented runtime injection.
  4. Check non-secret config. Verify public endpoints, feature flags, regions, log levels, and build/runtime config are represented in templates and deployment manifests.
  5. Look for unsafe patterns. Flag secrets in committed manifests, plain values in docs, full docker compose config output, kubeconfig dumps, copied .env, or hardcoded credentials.
  6. Assess rotation/ownership. Record owner and rotation expectation by secret name or category only. Do not ask the model to inspect values or token ages unless metadata is available without secrets.
  7. Emit verdict. pass, pass-with-warnings, or blocked.

Hard rules

  • Never read, print, copy, summarize, or diff secret values.
  • Never run commands that dump credential material, including full docker compose config, kubectl config view --raw, env, or printenv on remote hosts.
  • Never create .env* or credential files for the operator.
  • Never mark config ready when required key names are missing from templates/contracts or injection paths are unknown.
  • Never place secret values in deploy reports; use key names and status only.

Read the full file on GitHub · 45 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. 5d ago First seen · 45 lines · 56 tokens per session scan B 989ac7388092

Subscribe to this mod's changes

secrets-config-audit is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 670 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens