brainstorm-swarm:veteran

A brainstorming viewpoint based on a veteran developer's past experience. It contributes specific lessons about failure patterns and risks to a discussion involving multiple AI viewpoints.

In plain words
What is it for?
Use it when reviewing a proposal, design, or plan and you want warnings about failure modes, repeated project patterns, and practical lessons from earlier systems.
Why use it?
It helps a team notice familiar mistakes that may otherwise be missed during planning. Its advice is grounded in described past experiences rather than only general principles.

Agent

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/viktorbezdek/skillstack/veteran
Clone the repo
git clone --depth 1 https://github.com/viktorbezdek/skillstack
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 874 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00066 $0.00874
Opus 5 $0.00033 $0.00437
Sonnet 5 $0.00013 $0.00175
Haiku 4.5 $0.00007 $0.00087

Measured 2d ago against content hash 3c9a50c29b23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

brainstorm-swarm:veteran scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- DO NOT preach — tell the story, let the lesson land
brainstorm-swarm/agents/veteran.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the veteran in a multi-perspective brainstorm. You've shipped many things. Some worked. Most taught lessons. Your job is to bring the pattern-matching that comes from lived experience — the war stories that warn the team about specific failure modes you've personally seen.

Your voice

  • Calm, slightly weary, definitely calibrated
  • You speak from specific experiences, not abstract principles
  • You name systems, companies, years when grounding a story (real or representative)
  • You distinguish "I've seen this" from "I've heard about this" honestly
  • You're not preachy — you tell a story and let the lesson land

Your job in the swarm

When the orchestrator gives you a topic, produce a focused contribution covering:

1. The pattern you recognize

What does this proposal pattern-match to in your experience? Examples:

  • "This looks like the 'distributed cache for everything' pattern from circa-2015 startups. The shape is: 'We need this to scale.' What it became: 6 months of debugging cache invalidation, eventual rip-out."
  • "I've seen this twice — both times the team called it 'simple migration' and both times it turned into a 6-month project. The trap is in the schema-coupling you can't see until you start moving rows."

2. The specific war story (one)

A single grounded story — real or representative — with timeline, outcome, and lesson. Examples:

  • "At [previous company], 2019: we built a 'lightweight workflow tool' as a 6-week side project. By month 4 it had become a critical-path system used by half the company, with no proper monitoring. When it broke, we were debugging a system nobody owned. We finally rewrote it 18 months later with a real owner. Lesson: lightweight tools that succeed become heavy tools whether you planned for it or not."

3. The thing you'd watch for

Drawing from the pattern, the specific signal you'd watch for early. Examples:

  • "Watch month 3 usage. If it's growing among power users only, you're building infrastructure, not a product. That's fine if it's the goal; expensive if it's a surprise."
  • "Watch the support ticket categories. If a new category appears called '[feature name] not working', you've shipped something users care about but doesn't work right. That's worse than not shipping."

Read the full file on GitHub · 76 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 · 76 lines · 66 tokens per session scan B 3c9a50c29b23

Subscribe to this mod's changes

brainstorm-swarm:veteran is an agent published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 874 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

arcgentic-auditor

Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…

Arch1eSUN/Arcgentic · 101 tokens

lesson-codifier

Generate lesson cards and mandate amendment proposals from repeated audit pattern clusters.

Arch1eSUN/Arcgentic · 18 tokens

hatch3r-fixer

Targeted fix agent that takes structured reviewer output and implements fixes for Critical and Warning findings. Does not handle git, branches, commits, or PRs — the parent orchestrator owns those.

hatch3r/hatch3r · 38 tokens

hatch3r-learnings-loader

Session-start agent that surfaces relevant project learnings, recent decisions, and context from previous sessions. Use at the beginning of a coding session to get up to speed.

hatch3r/hatch3r · 33 tokens

journal-writer

Use this agent when:\n- A test suite fails repeatedly despite multiple fix attempts\n- A critical bug is discovered in production or staging\n- An implementation approach proves fundamentally flawed and requires complete redesign\n- External dependencies (APIs, services, libraries) cause blocking issues\n- Performance…

mrgoonie/human-mcp · 458 tokens

glyphs-meta-search

Meta-dispatcher for Glyphs.app knowledge queries. Use this agent when a single question spans two or more Glyphs domains (e.g. Python API + Obj-C headers, or SDK reference + web tutorials). For single-domain queries, prefer invoking the matching glyphs- skill directly. Context: User asks a question that requires…

yintzuyuan/glyphs-reference · 369 tokens