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 99999G/AK47 --skill ak47-plugin-generatorgit clone --depth 1 https://github.com/99999G/AK47Wrote 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/99999g/ak47/ak47-plugin-generator)<a href="https://agentmods.dev/skills/99999g/ak47/ak47-plugin-generator"><img src="https://agentmods.dev/badge/skills/99999g/ak47/ak47-plugin-generator.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 5.1 | $0.00032 | $0.00694 |
| Opus 5 | $0.00016 | $0.00347 |
| Sonnet 5 | $0.00006 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade C, and why
ak47-plugin-generator scanned grade C 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 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.
Encoded or obfuscated payloadhighSupply chain
base64 or hex that is decoded and executed hides what actually runs from anyone reading the file.
- Do not generate OS-specific shell wrappers such as `echo %s|base64 -d|bash` unless the target OS and shell are confirmed. How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AK47 Plugin Generation
Overview
Generate AK47 plugin YAML using the official syntax docs. Focus on correctness, minimal defaults, and a closed exploitation flow.
Language Handling
Apply these internationalization rules:
- If the user explicitly requests a language, follow it.
- Otherwise, detect language from the latest user message.
- If Chinese and English are mixed, prefer the language used for the primary task description.
- Keep the output language consistent within a single response.
- Use the matching syntax doc:
- Chinese: references/SYNTAX.zh.md
- English: references/SYNTAX.en.md
Workflow
- Scope the plugin.
- Collect vendor/product, vulnerability name, exploit type (U/C/D/M), and protocol (http/tcp/udp/ws/websocket).
- Define the expected outcome (command output, file download, upload verification, memshell confirmation).
- Map the attack chain.
- List request sequence, required headers/cookies/tokens, and extraction points.
- Identify what must be stored in
varsfor reuse.
- Design defaults.
- Provide minimal but runnable
defaultvalues. - Do not add parameters that are not used by the exploit flow.
- Provide minimal but runnable
- Build rules.
- Each rule performs one step and has explicit success conditions.
- Use
varsin rules to capture dynamic data for later steps.
- Compose
expr.- Orchestrate the rule flow and ensure it returns a boolean.
- Validate structure.
- Use
plugin_checkwhen MCP is available. - Also re-check all fields against the selected syntax doc.
- Ensure template strings use only
{{}}interpolation.
- Use
Required Rules
- File naming format:
Product/VulnName#Type.ymlwhere Type isU/C/D/M. defaultmust only use allowed fields from syntax docs.- Request templates only allow
{{}}interpolation. exprmust be boolean and orchestrate rule flow.- Prioritize echo command execution or MemShell confirmation over OOB for RCE unless the exploit only supports OOB-style verification.
- Use
printto present exploit results together with relevant verification details. - Do not generate OS-specific shell wrappers such as
echo %s|base64 -d|bashunless the target OS and shell are confirmed. - Use a dedicated boundary variable for multipart uploads that use
----WebKitFormBoundary{{...}}, and do not mix it with unrelated variables. - For MemShell plugins, use assets/MemShell.json to select valid tool/server/method combinations.
What ships with it
3 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.
- 8d ago First seen · 67 lines · 32 tokens per session scan C cb158b7ce5b3
ak47-plugin-generator is a skill published in the GitHub repository 99999G/AK47 (11 stars, last pushed 27d ago), licensed MIT. It adds 32 tokens to every session and 694 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (encoded or obfuscated payload). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
offensive-edr-evasion
EDR evasion offensive checklist: hook unhooking (user/kernel), direct syscalls, PPID spoofing, process injection variants, AMSI bypass, ETW patching, memory encryption, and behavior-based evasion. Use when planning EDR bypass during red team engagements or researching AV/EDR evasion techniques.
offensive-initial-access
Initial access techniques checklist: phishing (spear/smishing), credential stuffing, exposed service exploitation, supply chain attacks, watering hole, VPN/RDP brute force, public-facing application exploitation. Maps to MITRE ATT&CK TA0001. Use when planning initial access phases of red team engagements.
offensive-mitigations
Security mitigation reference and bypass catalog: ASLR, DEP/NX, RELRO, stack canaries, CFI, sandboxing, seccomp. Covers both detection of enabled mitigations and known bypass techniques. Use when assessing target hardening or planning exploit mitigation bypasses.
offensive-k8s-attacks
Kubernetes cluster attack techniques covering the full attack lifecycle from initial foothold in a pod to cluster-wide compromise. Covers service account token theft and impersonation, RBAC misconfiguration exploitation including wildcard permissions and privilege escalation via role binding, direct etcd access for…
offensive-exploit-development
Exploit development operational guide: environment setup, debugging workflow, PoC development lifecycle, writing reliable exploits, using pwntools/pwndbg, heap exploitation techniques, and weaponization considerations. Use when actively developing exploits or setting up an exploit dev environment.