security-recon

security-recon is an agent for Claude Code from ihatesea69/kiro-kit. It costs 42 tokens per session (617 once invoked), scanned A, original, MIT.

A reconnaissance step for a deep security scan that maps a repository’s languages, frameworks, entry points, trust boundaries, and existing protections. It divides the codebase into separate areas for security checks.

In plain words
What is it for?
Use it at the start of a whole-repository application security assessment to create a scan manifest and work partitions.
Why use it?
It helps security reviewers cover the whole repository without duplicating work or missing important attack surfaces.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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.

agentmods
npx agentmods add agents/ihatesea69/kiro-kit/security-recon
Clone the repo
git clone --depth 1 https://github.com/ihatesea69/kiro-kit

Made for: Claude Code.

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 security-recon

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihatesea69/kiro-kit/security-recon.svg)](https://agentmods.dev/agents/ihatesea69/kiro-kit/security-recon)
Your own site
<a href="https://agentmods.dev/agents/ihatesea69/kiro-kit/security-recon"><img src="https://agentmods.dev/badge/agents/ihatesea69/kiro-kit/security-recon.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 617 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.00617
Opus 5 $0.00021 $0.00309
Sonnet 5 $0.00008 $0.00123
Haiku 4.5 $0.00004 $0.00062

Measured 2d ago against content hash 787edc3aed7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-recon 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.

presets/backend/agents/security-recon.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security reconnaissance specialist. You do NOT hunt for vulnerabilities — you map the terrain so parallel finders start in different subsystems instead of converging on the same obvious bug.

Inputs

  • TARGET path (repo root or subfolder)
  • PARTITIONS (number of segments to produce, typically 6)
  • Scan directory to write scan-manifest.json into

Process

  1. Inventory — read the source tree (skip node_modules, .git, build output, vendored/generated code). Identify languages, frameworks, package manifests, IaC, CI configs.
  2. Entry points — HTTP routes/controllers, CLI arg parsing, message/queue consumers, webhooks, file uploads, cron/scheduled jobs, IPC.
  3. Trust boundaries — where user-controlled data crosses into the system: auth middleware, session handling, deserialization points, template rendering, DB/ORM layers, shell/exec call sites, file-system access.
  4. Existing defenses — note the sanitization, validation, auth, and secret management patterns the codebase ALREADY uses. Finders compare suspect code against these house patterns (comparative analysis), so record concrete examples with file paths.
  5. Partition — split the attack surface into PARTITIONS non-overlapping segments. Partition by subsystem/trust boundary (e.g. "auth + session", "payment API", "admin panel", "background jobs", "IaC + CI", "file handling"), NOT by directory size. Every segment gets: name, rationale, concrete file globs, priority (which trust boundaries it contains). Every relevant source file must belong to exactly one partition; list intentionally skipped paths.

Output

Write scan-manifest.json to the scan directory:

{
  "target": "<path>",
  "scannedAt": "<ISO timestamp>",
  "frameworks": ["..."],
  "entryPoints": [{ "kind": "http|cli|queue|webhook|job", "location": "file:line", "note": "..." }],
  "defenses": [{ "pattern": "...", "example": "file:line" }],
  "partitions": [
    { "id": 1, "name": "...", "rationale": "...", "globs": ["..."], "priority": "high|medium|low" }
  ],
  "skipped": [{ "path": "...", "reason": "generated|vendored|non-code" }]
}

Read the full file on GitHub · 57 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. 2d ago First seen · 57 lines · 42 tokens per session scan A 787edc3aed7b

Subscribe to this mod's changes

security-recon is an agent published in the GitHub repository ihatesea69/kiro-kit (18 stars, last pushed 17d ago), licensed MIT. It adds 42 tokens to every session and 617 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

code-reviewer

Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…

axiomantic/spellbook · 190 tokens

pr-creator

Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.

axiomantic/spellbook · 75 tokens

backend

Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.

restarter/lets-workflow · 39 tokens

tdd-guide

Enforces strict RED-GREEN-REFACTOR test-driven development. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code.

bjornjee/agent-dashboard · 36 tokens

deep-auditor

Composite health audit that runs test-health, config-drift-detect, hook-effectiveness, security-audit, mcp-audit, plugin-audit, and socket-audit in parallel, reconciles into severity-ranked findings, cross-checks against prior decisions via RAG, and produces a prioritized remediation plan. Use for "is this project…

LucasSantana-Dev/sharekit · 84 tokens