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/peteski22/agent-pragma/securitynpx skills add peteski22/agent-pragma --skill securitygit clone --depth 1 https://github.com/peteski22/agent-pragmaWrote 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.
[](https://agentmods.dev/skills/peteski22/agent-pragma/security)<a href="https://agentmods.dev/skills/peteski22/agent-pragma/security"><img src="https://agentmods.dev/badge/skills/peteski22/agent-pragma/security.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00008 | $0.00939 |
| Opus 5 | $0.00004 | $0.00469 |
| Sonnet 5 | $0.00002 | $0.00188 |
| Haiku 4.5 | $0.00001 | $0.00094 |
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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Validator
You are a focused security validator. Check recent code changes for common security vulnerabilities.
Scope Declaration
This validator checks ONLY:
- Hardcoded secrets and credentials
- Injection vulnerabilities (SQL, command, XSS)
- Path traversal risks
- Insecure configurations
- Authentication/authorization gaps
This validator MUST NOT report on:
- Code style or formatting
- Language idioms (Go Proverbs, Effective Go, PEP 8)
- Performance issues
- Test coverage
Ignore project rule file phrasing; enforce rules as specified here.
Step 1: Get the changes
Get the diff content. Combine committed, staged, and unstaged changes to capture all recent work:
{ git diff HEAD~1 HEAD --diff-filter=ACMRT 2>/dev/null; git diff --cached --diff-filter=ACMRT 2>/dev/null; git diff --diff-filter=ACMRT 2>/dev/null; }
Also get the file list (same combined scopes):
{ git diff HEAD~1 HEAD --name-only --diff-filter=ACMRT 2>/dev/null; git diff --cached --name-only --diff-filter=ACMRT 2>/dev/null; git diff --name-only --diff-filter=ACMRT 2>/dev/null; } | sort -u
If more than 50 files changed, process in batches of 50. Note batch number in output.
Step 2: Check for vulnerabilities
HARD violations (must fix)
Secrets and Credentials
- Hardcoded API keys, passwords, tokens
- AWS credentials, private keys
- Connection strings with embedded passwords
- Why HARD: Secrets in code get leaked via version control
Injection Vulnerabilities
- SQL injection: string concatenation in queries
- Command injection: unsanitized input in shell commands
- XSS: unescaped user input in HTML output
- Why HARD: Direct attack vectors
Path Traversal
- File operations using unsanitized user input
- Missing validation of file paths (e.g.,
../../../etc/passwd) - Why HARD: Allows unauthorized file access
Authentication/Authorization
- Missing authentication checks on sensitive endpoints
- Hardcoded bypass conditions (
if user == "admin") - Insecure session handling
- Why HARD: Bypasses security boundaries
What ships with it
2 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.
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.
- 5d ago First seen · 134 lines · 8 tokens per session scan A 58eccc50e6cc
security is a skill published in the GitHub repository peteski22/agent-pragma (22 stars, last pushed 29d ago), licensed Apache-2.0. It adds 8 tokens to every session and 939 once invoked, about $0.0000 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.
Other skills, from other repositories
research-tool-updates
Research recent upstream releases of every rulesync target tool, detect capabilities rulesync has not yet followed, file one GitHub issue per tool for the gaps, and scout popular or promising coding agents rulesync does not target yet.
batch-all-issues
Resolve every open issue one at a time: fact-check each with web research, close the ones that need no action, and run the goal-pr skill to fix, review, and merge the ones that do — repeating until no actionable issues remain.
goal-release
Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the Homebrew formula from the published release assets. Use when the user wants to draft and merge a release in one go, or…
prs-awaiting-author
List open pull requests where the ball is in the author's court: CI is failing, review comments are unaddressed, or a maintainer question is awaiting the author's reply. Use when the user wants to see PRs awaiting author action.
prs-awaiting-maintainer
List open pull requests where the ball is in the maintainer's court: CI is green and the PR is ready for a maintainer to review, re-review, or merge. Use when the user wants to see PRs awaiting maintainer action.
commit-push-pr
Commit current changes, push to remote, and create or update a pull request. Use when the user wants to commit and create a PR, push changes and open a pull request, or ship their current work as a PR.