DQIII8: Skill for Claude Code

.claude/skills/security-cycle/SKILL.md

security-cycle is a skill for Claude Code from senda-labs/DQIII8. It costs 55 tokens per session (693 once invoked), scanned A, original, MIT.

An automated security review process that repeatedly attacks a codebase, applies fixes, and checks the fixes again. Red-team means looking for security weaknesses as an attacker would; blue-team means fixing them.

In plain words
What is it for?
Use it to run security audits, fix critical or high-risk findings, track iterations, and produce reports of remaining risks.
Why use it?
It helps find serious security problems and verify that fixes hold across multiple review cycles.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/security-cycle/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

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 security-cycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/security-cycle/github.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/security-cycle)
Your own site
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/security-cycle"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/security-cycle/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-cycle

Your own site · 80×15
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/security-cycle"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/security-cycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 693 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00055 $0.00693
Opus 5 $0.00028 $0.00347
Sonnet 5 $0.00011 $0.00139
Haiku 4.5 $0.00006 $0.00069

Measured 10d ago against content hash 3f90f50b4116, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-cycle 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 10d 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.

.claude/skills/security-cycle/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/security-cycle — Iterative Security Hardening

Run red-team → blue-team → red-team cycles until the code is a bunker.

Usage

/security-cycle                     # Full cycle on current project
/security-cycle --max-iterations 5  # Limit iterations
/security-cycle $ARGUMENTS          # Cycle on specific path

Pipeline

Iteration N:

  1. Run /red-team → generates red-team report at tasks/audit/red-team-{date}-{N}.md
  2. Count CRITICAL + HIGH findings in the report
  3. If 0: STOP — code is hardened
  4. If > 0: Run /blue-team → fixes findings, generates tasks/audit/blue-team-{date}-{N}.md
  5. Run /red-team again → verify fixes hold + find new issues
  6. Repeat until CRITICAL + HIGH = 0 or max iterations reached (default: 10)

Stopping criteria

  • SUCCESS: Red-team finds 0 CRITICAL and 0 HIGH findings
  • MAX ITERATIONS: Limit reached — generate final report with remaining risks documented
  • NO PROGRESS: Two consecutive red-team reports with identical findings — stop, flag for manual review

After all iterations:

Generate: tasks/audit/security-cycle-{date}.md

# Security Cycle Report — {date}

## Iterations: {N}

| Iteration | Critical | High | Medium | Low | Fixed |
|-----------|----------|------|--------|-----|-------|
| 1 (red)   | 3        | 5    | 12     | 8   | —     |
| 1 (blue)  | —        | —    | —      | —   | 8 fixed |
| 2 (red)   | 0        | 1    | 9      | 6   | —     |
| 2 (blue)  | —        | —    | —      | —   | 1 fixed |
| 3 (final) | 0        | 0    | 7      | 4   | HARDENED |

## Final Security Score: {score}/100
## Vibe-Coding Patterns Fixed: {N}
## Kill Chains Eliminated: {N}
## Total Fixes Applied: {N}

Notes

  • Max 10 iterations by default (prevent infinite loops)
  • MEDIUM and LOW findings are documented but do not block completion
  • Each iteration generates separate red/blue reports for full audit trail
  • The security-cycle report is the master summary
  • After completion, commit all reports: git add tasks/audit/ && git commit -m "security: cycle {date} — {N} iterations, {score}/100"

Read the full file on GitHub · 70 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. 10d ago First seen · 70 lines · 55 tokens per session scan A 3f90f50b4116

Subscribe to this mod's changes

security-cycle is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 21d ago), licensed MIT. It adds 55 tokens to every session and 693 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.