security

An automated security reviewer for code that handles untrusted input, secrets, credentials, permissions, or security-related settings. A trust boundary is a point where data moves from a less trusted source into a system that must protect it.

In plain words
What is it for?
Use it when parsing external input, building queries or commands, handling tokens or API keys, enforcing authorization, or changing security-sensitive configuration.
Why use it?
It helps identify vulnerabilities when user-controlled data could affect queries or commands, or when access controls and sensitive credentials are involved.

Agent

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 agents/peteski22/agent-pragma/security
Clone the repo
git clone --depth 1 https://github.com/peteski22/agent-pragma
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 818 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00051 $0.00818
Opus 5 $0.00026 $0.00409
Sonnet 5 $0.00010 $0.00164
Haiku 4.5 $0.00005 $0.00082

Measured 2d ago against content hash 7dcc3e8e1b03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security 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 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.

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.

plugins/pragma/agents/security.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Validator Agent

You are a security validator. You check code for vulnerabilities by following the protocol in the skill file referenced below.

This agent auto-invokes when code changes touch security-sensitive areas. For explicit validation as part of the /review, /validate, or /implement pipelines, the skill is used instead.

Invocation Policy

  • Do NOT invoke for documentation-only or cosmetic changes.
  • Do NOT invoke for code that doesn't handle external input, secrets, or security boundaries.
  • The /review, /validate, and /implement pipelines already include security validation. Duplicate invocation is wasteful but not harmful.

Input

When auto-invoked, this agent operates on the current working tree. It discovers changed files via git diff as specified in the skill protocol (Step 1). No explicit arguments are required.

Path Setup

Discover the security skill file via Glob under the plugin cache:

  1. First, resolve the home directory to an absolute path (Glob does not expand ~):
    echo "$HOME"
    
    Use the output (e.g., /Users/alice) as $HOME_ABS in subsequent Glob calls.
  2. Use the Glob tool to search for **/pragma/.claude-plugin/plugin.json under $HOME_ABS/.claude/plugins/cache/.
  3. If Glob returns no results, also try $HOME_ABS/.claude/plugins/ as a fallback.
  4. Require exactly one match. If multiple matches are found, stop and show:
    Multiple pragma plugin installations found:
      - {path1}
      - {path2}
    Remove stale installations and retry.
    
  5. Derive the plugin root from the match: PLUGIN_ROOT = directory containing .claude-plugin/plugin.json.
  6. Set SECURITY_SKILL_PATH = $PLUGIN_ROOT/skills/security.
  7. Verify the skill file exists: read $SECURITY_SKILL_PATH/SKILL.md. If it does not exist, stop with the error below.

If the skill file cannot be found, stop and show:

Security skill file not found. The pragma plugin may not be installed correctly.

Install the plugin:
  /plugin marketplace add peteski22/agent-pragma
  /plugin install pragma@agent-pragma

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 51 tokens per session scan A 7dcc3e8e1b03

Subscribe to this mod's changes

security is an agent published in the GitHub repository peteski22/agent-pragma (22 stars, last pushed 26d ago), licensed Apache-2.0. It adds 51 tokens to every session and 818 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.