What is stack-skills?

A plugin containing six checks for common reasoning mistakes by AI coding agents, including deciding too early, inventing facts, following an initial assumption, and accepting an incomplete explanation.

Use it for scope checks, cross-verified research, adversarial review, idea sampling, reasoning traces, and pre-mortem analysis before or during coding work.

It encourages agents to clarify scope, verify information, review their work critically, explain their reasoning, and consider how a plan could fail.

stack-skills — Plugin by TheStack-ai

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.

Claude Code

/plugin marketplace add TheStack-ai/swing-skills

agentmods

npx agentmods add plugins/thestack-ai/swing-skills/marketplace

Clone the repo

git clone --depth 1 https://github.com/TheStack-ai/swing-skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

stack-skills 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.

.claude-plugin/marketplace.json · 19 lines

What it actually says

{
  "$schema": "https://cdn.agentskills.io/schemas/marketplace-v1.json",
  "name": "stack-skills",
  "version": "3.0.0",
  "display_name": "Stack Skills",
  "description": "6 cognitive firewalls for AI coding agents. Defends against premature closure, hallucination, anchoring bias, confirmation bias, black-box reasoning, and optimism bias.",
  "author": "thestack_ai",
  "owner": "thestack-ai",
  "homepage": "https://github.com/thestack-ai/stack-skills",
  "plugins": [
    {
      "name": "stack-skills",
      "description": "6 cognitive firewalls — scope clarification, cross-verified research, adversarial review, creativity sampling, reasoning tracing, and pre-mortem failure analysis.",
      "skills_path": "skills",
      "source": "https://github.com/thestack-ai/stack-skills"
    }
  ]
}

Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

plugin.json 474 B

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.

2d ago First seen · 19 lines scan A 79e42cb2853f

Subscribe to this mod's changes

stack-skills is a plugin published in the GitHub repository TheStack-ai/swing-skills (40 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Code review Data and AI Research ai-reasoning claude-code claude-code-skills claude-skills cognitive-firewall prompt-engineering

humanizer

Install Humanizer as a Claude plugin.

blader/humanizer · not measured

antimicrobial-resistance-scientist

Reasons from MIC distributions, ECOFFs, and phenotype–genotype concordance through EUCAST/CLSI AST, CARD/RGI and AMRFinderPlus resistomes, GLASS/WHONET/NARMS surveillance, carbapenemase/ESBL/MRSA mechanism panels, and heteroresistance PAP while treating breakpoint mixing, genotype-without-phenotype overclaim…

K-Dense-AI/scientific-agents · not measured

sound

Code taste as installable rules. Probe a repo's stack, select only the rules its code shows a surface for (evidence-cited per rule), confirm, and scaffold a browsable .claude/sound/ rule map (surfaced by the sound:prime skill). Installed rules are user-owned; re-runs reconcile.

saadshahd/moo.md · not measured

stack-skills