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 elevanaltd/HestAI-MCP --skill build-anti-patternsgit clone --depth 1 https://github.com/elevanaltd/HestAI-MCPWrote 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/elevanaltd/hestai-mcp/build-anti-patterns)<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/build-anti-patterns"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/build-anti-patterns/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/elevanaltd/hestai-mcp/build-anti-patterns"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/build-anti-patterns.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 | $0.00032 | $0.01482 |
| Opus 5 | $0.00016 | $0.00741 |
| Sonnet 5 | $0.00006 | $0.00296 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade B, and why
build-anti-patterns 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 9d 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: "*" How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===SKILL:BUILD_ANTI_PATTERNS=== META: TYPE::SKILL VERSION::"1.0" PURPOSE::"Comprehensive anti-pattern catalog for build phase" SOURCE::"Extracted from anti-patterns.oct.md"
§1::ISOLATED_EDITS SYMPTOMS::"'I just changed one function' → unexpected failures in distant components" EXAMPLE::"processUser(id)→processUser(userId): 15 call sites + db query builder + GraphQL resolver = 4hrs debugging" DETECT::[ "Changes without grepping usage", "Skip dependency analysis", "Quick fix mentality", "No test failures but prod breaks" ] PREVENT::[ "Ripple map before coding (git grep usage)", "Run full test suite (not just changed file)", "Check types (mypy/tsc)", "System impact analysis" ]
§2::FEATURE_BLOAT SYMPTOMS::"'Since I'm here I'll also...' → features nobody asked for" EXAMPLE::"Task: email validation. Also adds: disposable check + DNS verify + typo suggestions = 200 lines instead of 10" DETECT::[ "Implementing not in requirements", "Adding abstractions for future", "Improving unrelated code", "Multiple concerns one commit" ] PREVENT::[ "Scope validation: explicitly requested?", "Defer until needed (Rule of Three)", "Separate PRs for improvements", "One concern per commit" ]
§3::CONTEXT_DESTRUCTION SYMPTOMS::"'Comment is obvious, removing it' → deleting architectural rationale" EXAMPLE::"setTimeout comment explaining why not setInterval → deleted → future dev reintroduces bug" DETECT::[ "Deleting non-obvious comments", "Removing TODOs without resolution", "Stripping git history", "Cleanup PRs removing context" ] PREVENT::[ "Git handles versions, comments explain WHY not WHAT", "Preserve TODOs with explanations", "Architectural decisions in docs", "Commit messages explain WHY" ]
§4::PREMATURE_OPTIMIZATION SYMPTOMS::"'This could be faster' → optimization without profiling" EXAMPLE::"Optimize array iteration while real bottleneck is N+1 database queries" DETECT::[ "Optimizing without measuring", "Assuming bottlenecks", "Complexity added for theoretical speed", "Ignoring profiler results" ] PREVENT::[ "Profile first ALWAYS", "Optimize algorithms before code (O(n²)→O(n))", "Benchmark before/after", "Complexity cost must be justified" ]
§5::TEST_PROCRASTINATION SYMPTOMS::"'I'll add tests later' → tests fit code not requirements" EXAMPLE::"Implement feature → write tests after → tests pass but feature breaks edge cases" DETECT::[ "Tests added after code", "Commit message 'Add tests'", "Single commit with both test and implementation", "Test timestamp newer than implementation" ] PREVENT::[ "TDD discipline: RED→GREEN→REFACTOR", "Git history enforcement: test commit→feat commit", "Failing test proof required", "No merge without TDD evidence" ]
§6::ABSTRACTION_ADDICTION SYMPTOMS::"'Future flexibility' → abstractions for 2 use cases" EXAMPLE::"2 similar functions → DataProcessor class with generics → only 2 call sites + complex config" DETECT::[ "Abstraction before 3rd use", "Generic solutions for specific problems", "Indirection without clarity benefit", "Flexibility nobody needs" ] PREVENT::[ "Rule of Three: 1st concrete → 2nd note → 3rd abstract", "YAGNI: You Aren't Gonna Need It", "Abstractions must reduce cognitive load", "Must be understandable without docs" ]
§7::SNOWBALL_COMMITS SYMPTOMS::"100+ files in one PR → impossible to review" EXAMPLE::"Refactor user service + add feature + fix bugs + update deps = 247 files changed" DETECT::[ "PRs with 50+ files", "Multiple unrelated changes", "Commits with mixed concerns", "Reviewer comment: 'too large to review'" ] PREVENT::[ "Atomic commits: one logical change", "Feature flags for gradual rollout", "Separate refactor from features", "Stacked PRs: small incremental" ]
§8::DEPENDENCY_DRIFT SYMPTOMS::"Outdated dependencies → security vulnerabilities + compatibility issues" EXAMPLE::"[email protected]→18.0 without testing → breaking changes in hooks" DETECT::[ "Dependencies not updated 6mo+", "Security warnings ignored", "Version pinning without reason", "No dependency audit" ] PREVENT::[ "Regular updates: monthly review", "Security scanning: npm audit, Dependabot", "Test before update: integration suite", "Document version decisions" ]
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.
- 9d ago First seen · 177 lines · 32 tokens per session scan B 1609392a8366
build-anti-patterns is a skill published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 1,482 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.