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/firstp1ck/pi-coding-agent-forge/code-securitynpx skills add Firstp1ck/pi-coding-agent-forge --skill code-securitygit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forgeWhat 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 | $0.00048 | $0.02190 |
| Opus 5 | $0.00024 | $0.01095 |
| Sonnet 5 | $0.00010 | $0.00438 |
| Haiku 4.5 | $0.00005 | $0.00219 |
Grade A, and why
code-security 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
os.system(user_input) How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Security
Secret scanning, dependency vulnerability auditing, static analysis patterns, and supply chain security for the user's codebases.
Quick Start
Quick Repo Security Check
Run these in order for any repository:
# 1. Check for leaked secrets
grep -rn "sk-proj-\|sk-\|AKIA\|ghp_\|gho_\|github_pat_\|xoxb-\|xoxp-" --include="*.py" --include="*.ts" --include="*.js" --include="*.rs" --include="*.sh" --include="*.toml" --include="*.json" --include="*.yml" --include="*.yaml" --include="*.env" .
# 2. Check .gitignore covers sensitive files
cat .gitignore | grep -i "env\|secret\|key\|token\|credential"
# 3. Check for .env files in repo
find . -name ".env*" -not -path "./.git/*"
# 4. Run dependency audit (language-specific)
cargo audit # Rust
npm audit # JavaScript/TypeScript
pip-audit # Python (via pip install pip-audit)
Secret Scanning
Patterns to Detect
| Pattern | Regex | Severity |
|---|---|---|
| OpenAI API key | sk-proj-[A-Za-z0-9_-]{20,} |
Critical |
| OpenAI legacy key | sk-[A-Za-z0-9]{20,} |
Critical |
| AWS access key | AKIA[0-9A-Z]{16} |
Critical |
| GitHub PAT | ghp_[A-Za-z0-9]{36} |
Critical |
| GitHub OAuth | gho_[A-Za-z0-9]{36} |
Critical |
| GitHub App token | github_pat_[A-Za-z0-9_]{22,} |
Critical |
| Slack token | xox[bpors]-[A-Za-z0-9-]{10,} |
High |
| Telegram bot token | [0-9]{8,10}:AA[A-Za-z0-9_-]{33} |
High |
| Discord bot token | [MN][A-Za-z0-9]{23,}\.[A-Za-z0-9_-]{6}\.[A-Za-z0-9_-]{27,} |
High |
| JWT token | eyJ[A-Za-z0-9_-]*\.eyJ[A-Za-z0-9_-]*\.[A-Za-z0-9_-]* |
High |
| Generic API key | [Aa]pi[_-]?[Kk]ey.*[=:]\s*["'][A-Za-z0-9]{20,} |
Medium |
| Password in URL | ://[^:]+:[^@]+@ |
High |
| Private key header | `-----BEGIN (RSA | EC |
| Password assignment | [Pp]assword\s*[=:]\s*["'][^"']{8,} |
High |
Manual Secret Scan
# Comprehensive secret scan across a repo
grep -rn \
-e "sk-proj-" \
-e "sk-[A-Za-z0-9]\{20,\}" \
-e "AKIA[0-9A-Z]\{16\}" \
-e "ghp_" \
-e "gho_" \
-e "github_pat_" \
-e "xox[bpors]-" \
-e "BEGIN.*PRIVATE KEY" \
-e "password\s*=" \
-e "api_key\s*=" \
-e "secret\s*=" \
--include="*.py" --include="*.ts" --include="*.js" --include="*.rs" \
--include="*.sh" --include="*.toml" --include="*.json" --include="*.yml" \
--include="*.yaml" --include="*.env" --include="*.cfg" --include="*.ini" \
.
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 · 319 lines · 48 tokens per session scan A f605db3cb233
code-security is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (74 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 2,190 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
flow-nexus-platform
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.
github-code-review
Comprehensive GitHub code review with AI-powered swarm coordination.
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
github-workflow-automation
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management.
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…