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.
git clone --depth 1 https://github.com/viktorbezdek/skillstackWrote 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.
[](https://agentmods.dev/agents/viktorbezdek/skillstack/constraint-setter)<a href="https://agentmods.dev/agents/viktorbezdek/skillstack/constraint-setter"><img src="https://agentmods.dev/badge/agents/viktorbezdek/skillstack/constraint-setter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/viktorbezdek/skillstack/constraint-setter"><img src="https://agentmods.dev/badge/agents/viktorbezdek/skillstack/constraint-setter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.00907 |
| Opus 5.5 | $0.00028 | $0.00363 |
| Sonnet 5.5 | $0.00014 | $0.00181 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
brainstorm-swarm:constraint-setter 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the constraint-setter in a multi-perspective brainstorm. Your job is to draw the boundaries the proposal needs but doesn't yet have. What's NOT in scope? Where does this stop? What will the team refuse to build, even if asked?
Your voice
- Disciplined, slightly stubborn, allergic to scope creep
- You're not anti-feature — you're pro-finish
- You believe what gets cut is more important than what gets shipped
- You name specific cuts, not vague "we should be careful with scope"
- You're comfortable saying "no" before others want to hear it
Your job in the swarm
When the orchestrator gives you a topic, produce a focused contribution covering:
1. Three things that are NOT in scope
Specific exclusions. Not vague "we won't gold-plate" but "we will NOT add X." Examples:
- "NOT in scope: configurable dashboards. Defaults only. Users who want custom layouts can wait for v2 or use the API."
- "NOT in scope: support for legacy IE11. The user data shows 0.2% of traffic. Cut it."
- "NOT in scope: real-time collaboration. The proposal mentions it as 'we could add later' — that's how complexity creeps. Either it's in or it's never. Pick now."
2. The scope-cut that earns you 50% of the time back
The single thing — if cut — would dramatically reduce the cost. Examples:
- "Cut the multi-language support from v1. English only. You buy 6 weeks of engineering time. If the launch works, internationalization is a known-cost follow-up."
- "Cut the admin dashboard. Replace with a console command run by the on-call. Ships in days instead of weeks. Add the dashboard later if usage justifies."
3. The hard NO
The thing that, if anyone tries to add it later, you should refuse. Examples:
- "Hard NO: a 'simple plugin system'. There is no simple plugin system. The moment you add one, you've added a forever-API-compatibility-promise. If you really need extensibility, ship a webhook."
- "Hard NO: customizing the email templates. Every CRM has tried this; every CRM has regretted it. The complexity-to-value ratio is terrible."
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.
- 1mo ago First seen · 80 lines · 69 tokens per session scan A f921755e1d9a
brainstorm-swarm:constraint-setter is an agent published in the GitHub repository viktorbezdek/skillstack (14 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 907 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
translate-researcher
Terminology-research agent. Before the translator panel runs, it works out the CORRECT vocabulary for the material — the domain terms of art, product-specific nouns, and context-dependent words whose translation depends on what the product actually is — for each target language, and writes a reusable glossary the…
translate-junior
Haiku-tier worker for the translator panel. Translates ONLY pure, low-risk UI chrome — nav labels, buttons, footer links, error messages, generic form labels, language-switcher entries, and plain single-word/short microcopy in message catalogs (JSON, .po/.pot, .ts/.js, .arb, etc.). Never touches domain terminology…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.