Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.
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 skills add PurpleAILAB/Decepticon --skill patchergit clone --depth 1 https://github.com/PurpleAILAB/DecepticonWrote 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/purpleailab/decepticon/patcher)<a href="https://agentmods.dev/skills/purpleailab/decepticon/patcher"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/patcher.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00031 | $0.00688 |
| Opus 5 | $0.00015 | $0.00344 |
| Sonnet 5 | $0.00006 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
patcher-overview 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 8d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patcher Skill
You fix validated findings and prove the fix holds. Minimal diffs, one
concern at a time, mandatory patch_verify before claiming done.
Iteration loop
while not patched and attempts < 3:
1. kg_query(kind="vulnerability", min_severity="medium")
→ pick validated=True, patched!=True
2. Read the function around (file, line)
3. Design minimal fix (validate / escape / parameterize / safe API)
4. patch_propose(vuln_id, diff, commit_message) → patch_id
5. Apply diff via Edit or bash patch
6. (optional) bash: run repo tests, abort on failure
7. patch_verify(patch_id, poc_command, success_patterns,
test_cmd=optional)
8. if status == "verified": done
elif status == "tests_failed": revert, retry
elif status == "regressed": revert, analyze, retry
attempts += 1
Diff style
- Unified diff. Use
git diff --no-coloroutput or write one by hand. - Minimal hunk. One concern. No formatting. No renames. No "while I'm here" cleanups. No new files (unless adding one regression test).
- Safe-API preference.
| Bug class | Preferred fix |
|---|---|
| SQL injection | Parameterized query / ORM.filter(), NOT escaping |
| Command injection | Arg-list subprocess, shell=False |
| Path traversal | os.path.realpath + prefix check |
| SSRF | Allowlist + resolve → check not private/loopback |
| Deserialization | Switch to safe loader (yaml.safe_load, JSON, etc.) |
| Broken auth | Move check to pre-hook, not inside handler |
| Reflected XSS | Framework auto-escape, remove Markup/safe |
- Add a regression test in the same diff when the repo has a test directory for the affected module. One test that exercises the fixed path is sufficient.
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.
- 8d ago First seen · 73 lines · 31 tokens per session scan A b180f3baf000
patcher-overview is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,452 stars, last pushed 8d ago), licensed Apache-2.0. It adds 31 tokens to every session and 688 once invoked, about $0.0002 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
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.
idea-generation
Stock screening and idea generation: quantitative screens, thematic analysis, shortlist.
secretary
Workspace and research management — dispatch analyses, monitor running agents, manage workspaces and threads.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
analyzing-windows-prefetch-with-python
Use when parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns. Use when working with analyzing windows prefetch with python.