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 instructions/blisspixel/recon/agents-mdgit clone --depth 1 https://github.com/blisspixel/reconWhat 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 | $0.04670 | $0.04670 |
| Opus 5 | $0.02335 | $0.02335 |
| Sonnet 5 | $0.00934 | $0.00934 |
| Haiku 4.5 | $0.00467 | $0.00467 |
Grade A, and why
recon AGENTS.md 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 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.
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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: recon
This file is portable agent guidance in the agents.md format. AI coding tools that auto-detect AGENTS.md (Kiro, OpenAI Codex, Jules, Aider, others) load it automatically. Tools that don't (Claude Code, Cursor, Windsurf) can reference or include it from their own rules / skill files.
If you are an AI agent reading this in a recon-aware project: this is how to use the recon CLI and MCP server well.
What recon is
Public-metadata domain intelligence. Given an apex domain, recon returns hedged observations about that queried public namespace and its evidence-linked service and identity indicators. It uses public DNS, certificate transparency, and unauthenticated identity-discovery endpoints without credentials or API keys. Default collection performs no active scanning or port probing: authoritative DNS may observe resolver traffic, and MTA-STS is the only default target-owned HTTP/application request. Google CSE and BIMI certificate requests are explicit opt-in direct probes. recon ships as a CLI and an MCP server.
When to reach for recon
Use recon when the user wants to understand a domain's public-facing configuration:
- "Is
alpha.invalidon Microsoft 365? What's their tenant ID?" - "Score the email security on
gamma.invalid." - "What SaaS vendors does
beta.invalidappear to use?" - "Find related domains for
alpha.invalid." - "Compare the posture of
a.invalidandb.invalid."
Do not use recon for:
- Active scanning, port scans, or credentialed inventory.
- Vulnerability assessment or exploit checks.
- Company financials, news, hiring signals, or firmographic data.
- Generic target-owned application crawling. The only direct target interactions are the standards-compliant
mta-sts.{domain}request on the default path and the documented CSE / BIMI certificate probes when explicitly enabled.
If the user wants a verdict like "is this company secure," recon is not that tool. It surfaces observations; the user supplies the judgment.
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 · 279 lines · 4,670 tokens per session scan A 1eeb53d42b46
recon AGENTS.md is an instructions file published in the GitHub repository blisspixel/recon (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,670 tokens to every session, about $0.0233 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 2026-08-31.
Other instructions, from other repositories
user-scanner AGENTS.md
AGENTS.md instructions for kaifcodec/user-scanner, covering ai contributor guide, what this project is, start here (read before writing code), repository layout and adding a new module (the short version).
redamon AGENTS.md
AGENTS.md instructions for samugit83/redamon, covering redamon - agent ruleset (repository root), auto-invoke skills, critical rules - non-negotiable, code comments and tech stack.
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.
DorkAgent CLAUDE.md
Instructions for yee-yore/DorkAgent, covering claude.md, project overview, commands, running the tool and interactive mode (menu-driven interface).
CkSKILLS AGENTS.md
Instructions for zhaji2333/CkSKILLS, covering agents.md — 顶尖src漏洞挖掘专家（总纲 · 约束 · 技能调度）, 0. 核心身份与目标, 核心专长, 输出标准 and 1. 工作约束（必须遵守）.
European-Parliament-MCP-Server copilot-instructions.md
Instructions for Hack23/European-Parliament-MCP-Server, covering copilot instructions, 📋 required context files, project overview, development commands and 🎯 skills catalog (41 skills in .github/skills/).