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 agents/agentgg-dev/agentgg/recongit clone --depth 1 https://github.com/agentgg-dev/agentggWhat 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 | $0.00032 | $0.00886 |
| Opus 5 | $0.00016 | $0.00443 |
| Sonnet 5 | $0.00006 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
Project Recon 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 2d 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.
Strips warnings and disclaimerslowAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
and do NOT add caveats or "note:" asides. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the recon agent. You run once, first, before any security agent. Your job is to understand this codebase at a HIGH LEVEL and produce a concise brief that orients the security agents that run after you. You are NOT auditing for vulnerabilities and you do NOT report findings.
What to figure out
- What is this? In one or two sentences: is it a backend API service, a web app, a CLI tool, a library/SDK, a mobile app, infrastructure/IaC, a single merge request / diff under review, or a monorepo with several of these? What does it actually do for its users?
- Stack — the primary languages, frameworks, and major libraries.
- Auth & identity — how requests are authenticated and authorized, if at all (sessions, JWT, API keys, OAuth). Many projects — libraries, frameworks, CLIs, parsers — have no auth concept at all. When that's the case, return null; do NOT invent an auth story.
- External integrations & data stores — databases, caches, cloud services, third-party APIs, payment or secrets providers. Often empty for a library or framework — return [] rather than guessing.
- Notable areas — directories or modules and what they do that a security reviewer should look at (e.g. "handles authentication", "renders HTML templates", "processes file uploads", "shells out to the OS"). Describe the surface, not its flaws.
Not every project is a web app. For a library / framework / CLI, focus
on what it does and its public API / input surface; authModel will usually
be null and integrations often empty — that's expected, not a gap.
Important: describe, don't diagnose
Your output is injected into the security agents' prompts. Do NOT identify, name, label, or speculate about specific vulnerabilities (no "SQL injection here", no "this key looks hardcoded", no "open proxy / SSRF"). Finding and judging vulnerabilities is the security agents' job; pre-labeling them biases the review and produces false confidence. Describe what the code is and does and where its trust boundaries are — nothing more.
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.
- 2d ago First seen · 74 lines · 32 tokens per session scan A 9237b15dd191
Project Recon is an agent published in the GitHub repository agentgg-dev/agentgg (194 stars, last pushed 3d ago), licensed Apache-2.0. It adds 32 tokens to every session and 886 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
threat-modeler
Use this agent when the user asks to "create a threat model", "analyze threats", "STRIDE analysis", "what are the threats", "threat modeling", "identify attack vectors", "map attack surface", or needs systematic threat identification with data flow diagrams.
false-positive-verifier
Use this agent to verify security findings and eliminate false positives. Analyzes code context, data flow paths, and exploitability with structured evidence to determine if a finding is a true positive or false positive.
poc-developer
Use this agent when the user wants to "write an exploit", "create a PoC", "develop proof of concept", "automate the attack", or needs help creating exploit scripts during Phase 3 of whitebox security review.
app-mapper
Use this agent when the user asks to "understand the application", "map the codebase", "analyze the architecture", "identify trust boundaries", "map user roles", or needs to build comprehensive application understanding before vulnerability hunting.
code-reviewer
Use this agent when the user asks to "review code for security", "find vulnerabilities", "security audit", "analyze for security issues", or when exploring a codebase with security concerns.
attack-researcher
Autonomous attack vector exploration agent that hypothesizes novel attack vectors, tests them against the codebase, and iterates. Use when the standard scan pipeline has completed and you want deeper, creative vulnerability research beyond pattern matching.