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 tamnguyendinh/Anvien --skill repo-bootstrapgit clone --depth 1 https://github.com/tamnguyendinh/AnvienWrote 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/tamnguyendinh/anvien/repo-bootstrap)<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/repo-bootstrap"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/repo-bootstrap/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/tamnguyendinh/anvien/repo-bootstrap"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/repo-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.02424 |
| Opus 5 | $0.00008 | $0.01212 |
| Sonnet 5 | $0.00003 | $0.00485 |
| Haiku 4.5 | $0.00002 | $0.00242 |
Grade A, and why
repo-bootstrap 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.
How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Bootstrap
Goal: create the minimum complete source-of-truth package that lets an AI agent or developer start implementation without guessing. Do not force every repo into an app/backend/SaaS shape. Classify the repository first, then select the right lanes.
Core Rule
Bootstrap is decision work before coding. It must make the next implementation agent's choices explicit:
- what the repo is
- what it must and must not do
- which technologies are approved
- where boundaries are
- how to run, test, package, release, and verify it
- which decisions are still blocked
If a decision affects code, dependencies, public API, data shape, runtime behavior, deployment, or QA, do not leave it implicit.
Workflow
Run these phases in order.
[0] Repository Type Classification
[1] Project Context
[2] Architecture / Repo Blueprint
[3] Toolchain & Dependency Policy
[4] Conditional Domain Specs
[5] Technical Standards
[6] Environment, Packaging, Release
[7] Test & QA Strategy
[8] Handoff Checklist
Do not skip phase 0. The old fixed sequence of Database -> API -> DevOps is valid for many app repos, but wrong for many libraries, CLIs, docs repos, infrastructure repos, MCP servers, firmware, games, and data/ML repos.
Phase 0 - Repository Type Classification
Classify the repo before writing detailed specs.
Record:
## Repository Classification
- Repository type:
- Primary users:
- Runtime target:
- Main deliverable:
- Interface surface:
- Data persistence:
- Deployment/distribution:
- Required conditional lanes:
- Explicitly not applicable lanes:
Use this guide:
| Repository Need | Select Lane |
|---|---|
| Web app, fullstack app, backend API, SaaS product | App / Service |
| Reusable package, SDK, framework, internal library | Library / SDK |
| Command-line tool or developer utility | CLI |
| Terraform/Pulumi/CloudFormation/Kubernetes/platform config | Infrastructure / IaC |
| Data pipeline, analytics, ML/model repo | Data / ML |
| Native or cross-platform mobile app | Mobile |
| Browser extension | Browser Extension |
| MCP server, plugin, agent tool integration | MCP / Plugin |
| Docs/wiki/content-only repo | Documentation |
| Embedded, hardware, firmware | Embedded / Firmware |
| Game, graphics, simulation, 3D app | Game / Graphics |
| Electron/Tauri/native desktop app | Desktop App |
| Monorepo with multiple packages/apps | Monorepo |
| Multi-tenant SaaS | SaaS Multi-Tenant |
| Frontend with complex UI system | Design System |
| Blockchain/Web3 | Blockchain / Web3 |
What ships with it
5 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.
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 · 355 lines · 16 tokens per session scan A 2e4f03536fcc
repo-bootstrap is a skill published in the GitHub repository tamnguyendinh/Anvien (9 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 2,424 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
issue-triage
Triage and categorize GitHub issues with priority labels. Use when user says "triage issues", "check issues", "review open issues", or during regular maintenance of GitHub issue backlog.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
product-manager-toolkit
Use when the user needs product management workflows such as RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, go-to-market strategy, feature prioritization, research synthesis, or requirements documentation.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
mention-conventions
Display @-mention naming conventions and placement rules.
mention-lint
Lint @-mentions for style consistency and correctness.