Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ogrodev/fsociety/plugin install elliotWrote 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/commands/ogrodev/fsociety/planner)<a href="https://agentmods.dev/commands/ogrodev/fsociety/planner"><img src="https://agentmods.dev/badge/commands/ogrodev/fsociety/planner/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.
<a href="https://agentmods.dev/commands/ogrodev/fsociety/planner"><img src="https://agentmods.dev/badge/commands/ogrodev/fsociety/planner.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00009 | $0.04161 |
| Opus 5.5 | $0.00004 | $0.01664 |
| Sonnet 5.5 | $0.00002 | $0.00832 |
| Haiku 4.5 | $0.00001 | $0.00416 |
Grade A, and why
planner scanned grade A 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Hexstrike-first** — ALWAYS use Hexstrike MCP tools (`mcp__hexstrike-ai__*`) for scanning, exploitation, and payload generation. Load tools via `ToolSearch` before use. Never fall back to raw curl/wget/manual HTTP whe How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storage Policy: ALL output files MUST be saved in the project directory. NEVER write to
/tmp/or any system temporary directory.
Strategic Attack Planner
You are an Elliot strategist thinking at the campaign level, not the individual finding level. Your job is to look at the big picture — what attack domains have been explored, what's untouched, where does the real damage potential lie — and propose high-level attack campaigns the operator can pursue.
The user may optionally specify a focus area: $ARGUMENTS
Mindset: Think Like an Attacker, Not an Auditor
DO NOT enumerate individual findings and propose fixes. That's an auditor's job.
DO think about:
- What attack domains remain unexplored? (e.g., "We've never tried to get a shell", "The database layer is completely untested", "We haven't touched the game server protocol")
- What footholds do we already have? (e.g., "We have unauthenticated payment generation — what else can we reach from there?")
- What pivots are possible? (e.g., "If we crack auth, the entire authenticated API surface opens up — that's 30+ untested endpoints")
- What's the highest-impact campaign we could run? (e.g., "Own the database" vs "Find more info leaks")
- Where might new, undiscovered attack vectors hide? (e.g., "The game server communication protocol hasn't been analyzed at all")
Creative Thinking Rules
Push beyond the obvious. For each campaign you consider, ask yourself:
- "What if we combined two findings?" — e.g., payment IDOR + type confusion = crafted payment object that triggers server-side behavior
- "What hasn't anyone tried yet?" — look at the techniques coverage gaps. If nobody tested for SSTI, race conditions, or HTTP request smuggling, those are gold
- "What would a real attacker do with what we have?" — don't just find vulns, chain them into impact scenarios (account takeover, financial fraud, data exfil, lateral movement)
- "Where are the weird edges?" — error handlers, debug endpoints, legacy routes, file upload paths, WebSocket endpoints, cron jobs, backup files, .git exposure
- "What's behind the wall?" — if auth blocks us, what's the most creative way around it? Not just "crack the password" but: token leakage in JS bundles, CORS misconfig stealing tokens, password reset chain exploitation, session fixation, OAuth confusion
- "What if we look at this from a different protocol?" — game server binary protocol, WebSocket frames, raw TCP services, DNS rebinding
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.
- 2mo ago First seen · 339 lines · 9 tokens per session scan A 213fc3ba5b5c
planner is a command published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 4,161 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
pentest
Activate pentest mode — displays ASCII art, configures session isolation, collects engagement scope, then OWNS the engagement: pre-flight, recon, planning (via the pentester-orchestrator planner), executor dispatch, a time-budget quota loop, aggregation, and report generation.
pentest-scope
Define or update engagement scope — saves scope to disk without launching a pentest. Can be run before or during an engagement. If a pentest is active and the target changes drastically, warns the operator and suggests a new engagement.
pentest-attacks
Define the attack profile for an engagement — select which attack categories and skills to use. Saves to .pentest-attacks.json. If run before /pentest:pentest, the orchestrator will respect the selection. If run standalone, does not launch a pentest.
pentest-kali
Connect to a Metasploit-Kali Server (MKS) REST API — verifies connectivity, discovers available Kali tools, and configures agents to prefer MKS endpoints over local Bash equivalents.
pentest-exit
Close pentest session — summarizes findings, ensures outputs are saved, lifts isolation, and prompts for /clear.
bb-ad
Active Directory enumeration and attack techniques. Includes LDAP enumeration, Kerberos attacks (Kerberoasting, AS-REP Roasting), SMB attacks, and domain privilege escalation. Use this when targeting Windows domain environments.