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 agentmods add skills/theagenticguy/erpaval/tech-stack-buildernpx skills add theagenticguy/erpaval --skill tech-stack-buildergit clone --depth 1 https://github.com/theagenticguy/erpavalWhat 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 | $0.00274 | $0.02130 |
| Opus 5 | $0.00137 | $0.01065 |
| Sonnet 5 | $0.00055 | $0.00426 |
| Haiku 4.5 | $0.00027 | $0.00213 |
Grade A, and why
tech-stack-builder 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 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.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contents
| File | When to load |
|---|---|
references/orchestrator.md |
Running /build-stack — intake → parallel research → synthesis → ADRs |
references/opinionated-defaults.md |
Deciding health-check vs full-research per category |
references/search-strategies.md |
Configuring researcher agent tool use (Context7, exa, nova, etc.) |
references/health-check-criteria.md |
HEALTHY / CAUTION / WARNING classification for recommendations |
references/output-templates.md |
Format specs for the stack report, ADRs, comparison matrices |
references/domains/backend.md |
Backend researcher domain config |
references/domains/frontend.md |
Frontend researcher domain config |
references/domains/infra.md |
Infrastructure researcher domain config |
references/domains/aws.md |
AWS researcher domain config |
references/domains/devtools.md |
Dev-tooling researcher domain config |
references/stacks/typescript/ |
Settled TypeScript/React patterns — 15 library references |
references/stacks/python/ |
Settled Python patterns — core, CLI, API, data pipeline |
references/stacks/go/ |
Settled Go patterns — modules, golangci-lint, govulncheck, chi |
references/stacks/rust/ |
Settled Rust patterns — cargo, clippy, nextest, cargo-deny |
references/stacks/shared/ |
Cross-language tooling — mise, lefthook, security, CI/CD, containers |
templates/stack-report.md |
Full report skeleton (instantiated by orchestrator) |
templates/adr-template.md |
ADR format for significant choices |
templates/comparison-matrix.md |
Comparison matrix format |
templates/scaffold/ |
Ready-to-copy project scaffolds — python, typescript, go, rust |
What ships with it
44 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/domains/aws.md 6.4 KB
- references/domains/backend.md 1.0 KB
- references/domains/devtools.md 3.7 KB
- references/domains/frontend.md 1.8 KB
- references/domains/infra.md 3.3 KB
- references/health-check-criteria.md 4.0 KB
- references/opinionated-defaults.md 17 KB
- references/orchestrator.md 12 KB
- references/output-templates.md 4.9 KB
- references/search-strategies.md 7.1 KB
- references/stacks/go/core.md 4.4 KB
- references/stacks/python/api.md 1.9 KB
- references/stacks/python/cli.md 1.9 KB
- references/stacks/python/core.md 5.7 KB
- references/stacks/python/data-pipeline.md 2.2 KB
- references/stacks/rust/core.md 5.7 KB
- references/stacks/shared/ci-cd.md 12 KB
- references/stacks/shared/code-quality.md 2.9 KB
- references/stacks/shared/containers.md 7.6 KB
- references/stacks/shared/git-hooks.md 2.9 KB
- references/stacks/shared/mise-config.md 3.7 KB
- references/stacks/shared/security.md 9.6 KB
- references/stacks/typescript/amplify-aurora.md 2.6 KB
- references/stacks/typescript/cdk.md 2.5 KB
- references/stacks/typescript/core.md 5.6 KB
- references/stacks/typescript/dnd-kit.md 2.0 KB
- references/stacks/typescript/motion.md 1.5 KB
- references/stacks/typescript/node-api.md 2.7 KB
- references/stacks/typescript/react-three-fiber.md 1.8 KB
- references/stacks/typescript/tanstack-form.md 1.5 KB
- references/stacks/typescript/tanstack-query.md 1.5 KB
- references/stacks/typescript/tanstack-router.md 1.9 KB
- references/stacks/typescript/tanstack-table.md 2.0 KB
- references/stacks/typescript/ui-blocks.md 979 B
- references/stacks/typescript/visualization.md 2.4 KB
- references/stacks/typescript/webapp.md 5.2 KB
- references/stacks/typescript/xy-flow.md 42 KB
- templates/adr-template.md 2.0 KB
- templates/comparison-matrix.md 3.3 KB
- templates/scaffold/go.md 6.1 KB
- templates/scaffold/python.md 9.0 KB
- templates/scaffold/rust.md 7.8 KB
- templates/scaffold/typescript.md 8.1 KB
- templates/stack-report.md 5.3 KB
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.
- 2d ago First seen · 124 lines · 274 tokens per session scan A f7155a93a612
tech-stack-builder is a skill published in the GitHub repository theagenticguy/erpaval (27 stars, last pushed 3mo ago), licensed MIT. It adds 274 tokens to every session and 2,130 once invoked, about $0.0014 per session on Opus 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 skills, from other repositories
plan
Write a short implementation plan or a longer execution plan before coding. Use when starting new work, when a ticket needs clearer boundaries, when a change spans multiple files or interfaces, or when a multi-hour task needs a living plan.
ai-news-research
You produce a daily AI news digest. Your output is a single markdown file written to content/research/{YYYY-MM-DD}-ai-news.md and committed to a branch.
linkedin-post
You take a YouTube video transcript and produce a single LinkedIn post draft.
youtube-description
You take a YouTube video transcript and produce the video description (with timestamps) and chapter list.
research
Research video ideas for a topic, preview them, and add only approved non-duplicates to the configured Airtable content pipeline.
code-review
Review code changes for bugs, security issues, performance problems, and style violations. Use when asked to review code, a PR, or recent changes.