q-sec-stack

A command that investigates a company’s security tools, security team, and recent threats, keeping the findings in one continuously updated case file.

In plain words
What is it for?
Use it with a company name or domain to start or continue a security-stack intelligence case and update its history.
Why use it?
It gives repeated investigations one source of truth instead of scattering research across separate notes and files.

Command

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 commands/assafkip/huntkit/q-sec-stack
Clone the repo
git clone --depth 1 https://github.com/assafkip/huntkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,249 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 $0.00000 $0.01249
Opus 5 $0.00000 $0.00624
Sonnet 5 $0.00000 $0.00250
Haiku 4.5 $0.00000 $0.00125

Measured 2d ago against content hash e9c1e65e8968, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

q-sec-stack 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.

commands/q-sec-stack.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run or continue a security-stack intelligence investigation on a company. Maintains a single written case file (CASE.md) per company that holds all info in one place.

Arguments: $ARGUMENTS (company name or domain, e.g. "elite.com" or "Acme Corp")

When to use

  • Founder says "/q-sec-stack " to start or continue a security stack intel run
  • Goal: identify security tooling, team structure, threats (last 12mo); keep all of it in one written case file
  • Output feeds a downstream demo/product tool that converts intel into tool- and team-specific action items

One file rule (NON-NEGOTIABLE)

One CASE.md per company. That file is the only source of truth. No supplementary YAML, no split briefs, no scattered notes. Every run updates sections in place and appends to section 10 (Update History).

Template: templates/sec-stack-case/CASE.md Location in each case: investigations/case-NNN-<slug>/CASE.md

Preflight

  1. Read .active-case to see if a case already exists for this company
  2. Look for an existing case folder matching the slug (e.g. case-NNN-<company-slug>)
  3. If found: load CASE.md as source of truth; merge new findings into sections 2-9; append run entry to section 10
  4. If not found: scaffold a new case:
    • Next case number (increment from highest in investigations/)
    • Slug: company name lowercased, non-alphanum -> hyphens
    • cp -R templates/new-investigation investigations/case-NNN-<slug>
    • cp templates/sec-stack-case/CASE.md investigations/case-NNN-<slug>/CASE.md
    • Fill header fields (company, case ID, domain, as_of_date, status=active)
    • Write folder name to .active-case
    • Leave canonical/scope.md minimal or delete it -- CASE.md is authoritative for sec-stack cases

Entity disambiguation (MANDATORY FIRST PASS)

Before collection:

  1. Resolve the legal entity behind the company name (whois, DNS, LinkedIn, SEC EDGAR if public)
  2. If multiple candidates exist (e.g. "elite.com" -> Elite SEM vs Elite World Group vs Elite Singles), STOP and ask the founder which entity
  3. Record resolution in CASE.md section 2 (Entity & Scope)

Read the full file on GitHub · 96 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 · 96 lines · 0 tokens per session scan A e9c1e65e8968

Subscribe to this mod's changes

q-sec-stack is a command published in the GitHub repository assafkip/huntkit (51 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,249 tokens. 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 2026-08-30.