build-philosophy

build-philosophy is a skill for Claude Code from elevanaltd/HestAI-MCP. It costs 34 tokens per session (1,299 once invoked), scanned B, original, Apache-2.0.

A broad framework for making code changes with awareness of their effects on the rest of a software system. It emphasizes tracing imports, data flow, shared state, and the simplest change that meets the user need.

In plain words
What is it for?
Use it when planning or reviewing changes that may affect production behavior, caching, dependencies, shared state, or overall system complexity.
Why use it?
A small edit can affect distant parts of an application. This framework helps avoid adding maintenance burden or improving one part while breaking another.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it when planning or reviewing changes that may affect production behavior, caching, dependencies, shared state, or overall system complexity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elevanaltd/hestai-mcp/build-philosophy
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.

Any agent
npx skills add elevanaltd/HestAI-MCP --skill build-philosophy
Clone the repo
git clone --depth 1 https://github.com/elevanaltd/HestAI-MCP

Made for: Claude Code.

Wrote 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.

agentmods badge for build-philosophy

README.md
[![agentmods](https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/build-philosophy/github.svg)](https://agentmods.dev/skills/elevanaltd/hestai-mcp/build-philosophy)
Your own site
<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/build-philosophy"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/build-philosophy/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.

agentmods 80×15 button for build-philosophy

Your own site · 80×15
<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/build-philosophy"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/build-philosophy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,299 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00034 $0.01299
Opus 5 $0.00017 $0.00649
Sonnet 5 $0.00007 $0.00260
Haiku 4.5 $0.00003 $0.00130

Measured 10d ago against content hash 0d7d88813583, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

build-philosophy 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 10d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

allowed-tools: "*"
src/hestai_mcp/_bundled_hub/library/skills/build-philosophy/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

===SKILL:BUILD_PHILOSOPHY=== META: TYPE::SKILL VERSION::"2.0" PURPOSE::"Comprehensive build philosophy framework preventing accumulative complexity" SOURCE::"Consolidated from ~/.claude/skills/build-execution/*.oct.md"

§1::SYSTEM_AWARENESS_MANDATE CORE_PRINCIPLE::"Code change → System ripple → Understand ripples BEFORE modification"

SYSTEM_THINKING::[ MAP_IMPACT::[ "Trace all imports/uses of changed code", "Follow data flow dependencies", "Identify shared state impacts", "Document ripple paths explicitly" ], LOCAL_CHANGE_SYSTEM_CONTEXT::"Simple edit can break distant components - think globally", LOCAL_OPTIMIZATION_DEGRADES::"Faster function ≠ better system if breaks caching", MINIMAL_CODE_SERVES::"Essential complexity serves users, accumulative serves maintenance burden" ]

MAINTAIN_LIVING_SYSTEM::"Not editing text files - every change affects production"

§2::MINIMAL_INTERVENTION_PRINCIPLE DEFINITION::[ ESSENTIAL::"Code serving measurable user value", ACCUMULATIVE::"Code adding maintenance burden without proportional user value" ]

DECISION::"Could we achieve same outcome with simpler means?"

PROCESS::"Remove components until UX degrades → identify break point → restore last essential → minimal achieved"

ENFORCEMENT::[ JUSTIFICATION::"User problem? Why not extend existing? Simplification test?", EVIDENCE::"What removed? Break point found? Minimal restoration done?", SIGNOFF::"Reviewer verifies minimality credible, no obvious bloat" ]

§3::PHILOSOPHY_FRAMEWORK UNDERSTAND_SHAPE_ACT::[ UNDERSTAND::[ "What is the user problem?", "System connections and dependencies?", "Core assumptions and invariants?", "WARNING: 'just try this', 'probably works', 'not sure how'" ], SHAPE::[ "Simplest solution satisfying requirements", "Obvious to future readers (6mo test)", "Easy test isolation", "Minimal coupling", "PATTERNS: proven>novel, simple>clever, explicit>implicit" ], ACT::[ "TDD: failing test first", "Implement minimal solution", "Refactor for essential simplification only", "Commit atomically", "SCOPE: requested ≠ while_here, one concern per commit" ] ]

WISDOM_PATH::[ BETWEEN::"Complexity labyrinth ← minimal effective → Oversimplification sea", AVOID_LABYRINTH::"Over-abstracted, premature generalization, unjustified patterns", AVOID_OVERSIMPLIFICATION::"Unjustified duplication, skipping necessary abstractions", MINIMAL_EFFECTIVE::[ "Just enough abstraction to prevent duplication", "Just enough flexibility to handle known variations", "Just enough structure to maintain coherence" ] ]

§4::DECISION_GATES BEFORE_CODE::[ "Is this solving a user problem?", "Can we extend existing components?", "Is this feature explicitly requested?", "Are we solving a problem that doesn't exist yet?", "IF accumulative → DON'T ADD" ]

BEFORE_ABSTRACTION::[ "Rule of Three: 1st concrete → 2nd copy → 3rd abstract", "Does it reduce cognitive load?", "Is it understandable without docs?", "Cost if requirements change?", "IF mysterious → KEEP CONCRETE" ]

BEFORE_OPTIMIZATION::[ "Is this a measured bottleneck?", "Have we profiled first?", "Is the gain measured?", "PROFILE FIRST → IF not measured → DON'T OPTIMIZE" ]

BEFORE_TESTS::[ "Does this test user-facing behavior?", "Does it validate component contract?", "Will it catch real bugs?", "Testing behavior not implementation?", "IF not user-facing → RECONSIDER" ]

BEFORE_REFACTOR::[ "Does this improve clarity?", "Does it reduce complexity?", "Are tests still green?", "Will it make future changes easier?", "SAFETY: small steps, test after each, revert if fail", "IF behavior changes → NOT REFACTORING, IT'S A FEATURE" ]

§5::PRACTICAL_EXAMPLES RIPPLE_MAP_EXAMPLE::[ CHANGE::"processUser(id) → processUser(user)", DIRECT::"10 files need to pass user object", INDIRECT::"Tests need fixtures not IDs, API needs hydration, caching changes", FLOW::"DB queries move to callers, N+1 risk emerges", OUTCOME::"Simple signature change → 20 files + performance testing + staged migration" ]

Read the full file on GitHub · 154 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. 10d ago First seen · 154 lines · 34 tokens per session scan B 0d7d88813583

Subscribe to this mod's changes

build-philosophy is a skill published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 1,299 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens