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.
npx agentmods add skills/curiouslearner/devkit/secret-scannernpx skills add CuriousLearner/devkit --skill secret-scannergit clone --depth 1 https://github.com/CuriousLearner/devkitWhat 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 | $0.00017 | $0.05538 |
| Opus 5 | $0.00009 | $0.02769 |
| Sonnet 5 | $0.00003 | $0.01108 |
| Haiku 4.5 | $0.00002 | $0.00554 |
Grade C, and why
secret-scanner scanned grade C 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 2d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
ssh user@server "sed -i '/ssh-rsa AAAA.../d' ~/.ssh/authorized_keys" How it starts
The opening of the file, as written. The whole thing — 940 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secret Scanner Skill
Detect accidentally committed secrets, credentials, and sensitive information in code.
Instructions
You are a secret detection expert. When invoked:
-
Scan for Secrets:
- API keys and tokens
- Passwords and credentials
- Private keys and certificates
- Database connection strings
- OAuth tokens and secrets
- Cloud provider credentials (AWS, GCP, Azure)
- Encryption keys
-
Pattern Detection:
- Regex-based secret detection
- Entropy analysis for high-randomness strings
- Known secret patterns (AWS keys, GitHub tokens, etc.)
- Custom secret patterns
- File type analysis (.env, config files)
- Comment analysis (TODO: remove this key)
-
Contextual Analysis:
- Distinguish real secrets from examples/test data
- Check if secrets are in version control history
- Identify false positives
- Determine secret exposure scope
- Check if secrets are still active
-
Risk Assessment:
- Classify severity (Critical, High, Medium, Low)
- Determine potential impact
- Check if secret has been exposed publicly
- Assess exploitability
- Identify affected systems
-
Generate Report: Create comprehensive secret exposure report with remediation steps
Secret Types and Patterns
Cloud Provider Credentials
AWS
# AWS Access Key ID
AKIA[0-9A-Z]{16}
# AWS Secret Access Key
[0-9a-zA-Z/+=]{40}
# AWS Session Token
[A-Za-z0-9/+=]{200,}
Google Cloud
# GCP API Key
AIza[0-9A-Za-z-_]{35}
# GCP Service Account
"type": "service_account"
Azure
# Azure Storage Key
[a-zA-Z0-9+/]{88}==
# Azure Client Secret
[0-9a-zA-Z-_~]{34,}
Version Control Tokens
GitHub
# GitHub Personal Access Token
ghp_[0-9a-zA-Z]{36}
# GitHub OAuth Token
gho_[0-9a-zA-Z]{36}
# GitHub App Token
(ghu|ghs)_[0-9a-zA-Z]{36}
GitLab
glpat-[0-9a-zA-Z-_]{20}
Database Credentials
# MongoDB Connection String
mongodb(\+srv)?://[^\s]+
# PostgreSQL Connection String
postgres(ql)?://[^\s]+
# MySQL Connection String
mysql://[^\s]+
# Generic DB Password
(password|pwd|pass)\s*[:=]\s*['"][^'"]+['"]
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.
- 2d ago First seen · 940 lines · 17 tokens per session scan C 2ef48882d753
secret-scanner is a skill published in the GitHub repository CuriousLearner/devkit (27 stars, last pushed 10mo ago), licensed MIT. It adds 17 tokens to every session and 5,538 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…