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.
npx skills add RudyCity/superagent --skill preserving-productive-tensionsgit clone --depth 1 https://github.com/RudyCity/superagentWrote 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/skills/rudycity/superagent/preserving-productive-tensions)<a href="https://agentmods.dev/skills/rudycity/superagent/preserving-productive-tensions"><img src="https://agentmods.dev/badge/skills/rudycity/superagent/preserving-productive-tensions/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/skills/rudycity/superagent/preserving-productive-tensions"><img src="https://agentmods.dev/badge/skills/rudycity/superagent/preserving-productive-tensions.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 | $0.00024 | $0.01044 |
| Opus 5 | $0.00012 | $0.00522 |
| Sonnet 5 | $0.00005 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
Preserving Productive Tensions 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 8d 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.
This is a copy
100% identical to Preserving Productive Tensions — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preserving Productive Tensions
Overview
Some tensions aren't problems to solve - they're valuable information to preserve. When multiple approaches are genuinely valid in different contexts, forcing a choice destroys flexibility.
Core principle: Preserve tensions that reveal context-dependence. Force resolution only when necessary.
Recognizing Productive Tensions
A tension is productive when:
- Both approaches optimize for different valid priorities (cost vs latency, simplicity vs features)
- The "better" choice depends on deployment context, not technical superiority
- Different users/deployments would choose differently
- The trade-off is real and won't disappear with clever engineering
- Stakeholders have conflicting valid concerns
A tension needs resolution when:
- Implementation cost of preserving both is prohibitive
- The approaches fundamentally conflict (can't coexist)
- There's clear technical superiority for this specific use case
- It's a one-way door (choice locks architecture)
- Preserving both adds complexity without value
Preservation Patterns
Pattern 1: Configuration
Make the choice configurable rather than baked into architecture:
class Config:
mode: Literal["optimize_cost", "optimize_latency"]
# Each mode gets clean, simple implementation
When to use: Both approaches are architecturally compatible, switching is runtime decision
Pattern 2: Parallel Implementations
Maintain both as separate clean modules with shared contract:
# processor/batch.py - optimizes for cost
# processor/stream.py - optimizes for latency
# Both implement: def process(data) -> Result
When to use: Approaches diverge significantly, but share same interface
Pattern 3: Documented Trade-off
Capture the tension explicitly in documentation/decision records:
## Unresolved Tension: Authentication Strategy
**Option A: JWT** - Stateless, scales easily, but token revocation is hard
**Option B: Sessions** - Easy revocation, but requires shared state
**Why unresolved:** Different deployments need different trade-offs
**Decision deferred to:** Deployment configuration
**Review trigger:** If 80% of deployments choose one option
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.
- 8d ago First seen · 153 lines · 24 tokens per session scan A c627a7612695
Preserving Productive Tensions is a skill published in the GitHub repository RudyCity/superagent (21 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,044 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Preserving Productive Tensions, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…