agents-md-reconnaissance

agents-md-reconnaissance is a skill for Claude Code, Codex from CrypticSwarm/Swarmforge. It costs 62 tokens per session (1,493 once invoked), scanned A, original, MIT.

A codebase-research skill for creating or reviewing an AGENTS.md file, which gives coding agents instructions specific to a directory.

In plain words
What is it for?
Use it to explore a directory, test its instructions against real coding tasks, refine the documentation, and review it for gaps or unnecessary detail.
Why use it?
It checks whether the file reflects the real structure, conventions, and workflows of the code instead of relying on guesses or incomplete notes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md.

Good fit Use it to explore a directory, test its instructions against real coding…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/crypticswarm/swarmforge/agents-md-reconnaissance
Install

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.

Any agent
npx skills add CrypticSwarm/Swarmforge --skill agents-md-reconnaissance
Clone the repo
git clone --depth 1 https://github.com/CrypticSwarm/Swarmforge

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agents-md-reconnaissance

README.md
[![agentmods](https://agentmods.dev/badge/skills/crypticswarm/swarmforge/agents-md-reconnaissance.svg)](https://agentmods.dev/skills/crypticswarm/swarmforge/agents-md-reconnaissance)
Your own site
<a href="https://agentmods.dev/skills/crypticswarm/swarmforge/agents-md-reconnaissance"><img src="https://agentmods.dev/badge/skills/crypticswarm/swarmforge/agents-md-reconnaissance.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.01493
Opus 5 $0.00031 $0.00746
Sonnet 5 $0.00012 $0.00299
Haiku 4.5 $0.00006 $0.00149

Measured 6d ago against content hash f7e18ac9897f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agents-md-reconnaissance 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 6d 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.

skills/agents-md-reconnaissance/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What This Skill Does

Runs a structured, multi-phase reconnaissance to produce (or refine) a directory-specific AGENTS.md that gives future agent sessions the context they need to work effectively in that part of the codebase.

Workflow Overview

Four phases, executed in order:

  1. Explore -- Build an initial AGENTS.md from codebase exploration
  2. Stress-Test -- Spawn subagents with real tasks derived from git history to find gaps
  3. Refine -- Incorporate subagent findings into the AGENTS.md
  4. Review -- Run a review agent to catch inconsistencies and trim noise

Phase 1: Explore

Goal: Produce a first-draft AGENTS.md for the target directory.

  1. Read the target directory listing to understand the file landscape.
  2. Identify the major subsystems by reading key entry points, config files, and index/barrel files.
  3. Use the Task tool with explore agents to investigate:
    • Architecture and data flow (how does a request/operation flow through the code?)
    • Key abstractions and class hierarchies
    • Naming conventions and domain terminology
    • Configuration patterns and registration mechanisms
    • Common procedures (how are new features of each type typically added?)
  4. Write the initial AGENTS.md at the target path. Structure it as:
    • Architecture Overview -- One-paragraph orientation
    • Naming Conventions -- Place near the top so terms are defined before use
    • Key Files -- Curated list with one-line descriptions (not exhaustive)
    • Subsystem sections -- One section per major subsystem, covering concepts an agent needs to make correct decisions (not implementation minutiae)
    • Common Procedures -- Step-by-step checklists for recurring task types

Writing guidelines:

  • Optimize for agent decision-making, not human onboarding.
  • Avoid line-number references (they drift on any edit).
  • Define conventions once, in one place, and reference from elsewhere.
  • Prefer high-level summaries over implementation details an agent would verify in code anyway.
  • Keep under 500 lines. If longer, trim low-signal content.

Read the full file on GitHub · 146 lines

Changes

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.

  1. 6d ago First seen · 146 lines · 62 tokens per session scan A f7e18ac9897f

Subscribe to this mod's changes

agents-md-reconnaissance is a skill published in the GitHub repository CrypticSwarm/Swarmforge (2 stars, last pushed 7d ago), licensed MIT. It adds 62 tokens to every session and 1,493 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens