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 Krastanov/JuliaLLMAgentSkills --skill document-repository-v-modelgit clone --depth 1 https://github.com/Krastanov/JuliaLLMAgentSkillsWrote 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/krastanov/juliallmagentskills/document-repository-v-model)<a href="https://agentmods.dev/skills/krastanov/juliallmagentskills/document-repository-v-model"><img src="https://agentmods.dev/badge/skills/krastanov/juliallmagentskills/document-repository-v-model/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/krastanov/juliallmagentskills/document-repository-v-model"><img src="https://agentmods.dev/badge/skills/krastanov/juliallmagentskills/document-repository-v-model.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 | $0.00089 | $0.01238 |
| Opus 5 | $0.00044 | $0.00619 |
| Sonnet 5 | $0.00018 | $0.00248 |
| Haiku 4.5 | $0.00009 | $0.00124 |
Grade A, and why
document-repository-v-model 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 12d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Repository V-Model
Build durable AGENTS.md routers and .agents/context/ documentation. Create a V-model
only as a temporary coordination artifact for an initial design or a holistic review.
Start
- Read every applicable repository instruction before inspecting or changing files.
- Establish the repository boundary, worktree rules, code roots, existing documentation, and developer authority.
- Choose exactly one workflow:
- Initial design: no implementation exists yet; turn a rough prompt into an implementation-ready design through developer interviews.
- Holistic review: compare an existing codebase with developer-confirmed goals to find design defects and missing implementation.
- Documentation maintenance: improve persistent agent guidance without a V-model.
- Preserve useful material and user changes. Treat code and tests as evidence of current behavior, not proof of intended behavior.
Read subagent playbooks only when delegation is permitted and the selected workflow benefits from independent lanes.
Do not create or maintain a V-model for routine feature work, releases, or ordinary documentation updates. Once a codebase has been implemented and holistically reviewed, the cost and drift risk of a persistent parallel specification outweigh its value.
Run an Initial Design
Read discovery and interviews, then read V-model and traceability.
- Before writing code, interview the developer in short rounds about users, scenarios, boundaries, failure behavior, constraints, non-goals, interfaces, and acceptance.
- Draft and confirm a temporary
.agents/v-model/that makes the rough prompt precise enough for independent agents to implement nonoverlapping parts. - Plan objective verification with the requirements. Keep implementation choices and
working instructions in
.agents/context/, not in normative records. - Develop the persistent routers and context while implementation proceeds.
- Reconcile the implementation, verification evidence, and developer intent.
- Move durable usage and development knowledge into agent documentation. Record any unfinished behavior there as brief, actionable current gaps.
- Delete
.agents/v-model/and every link or ID that depends on it before final handoff.
What ships with it
18 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.
- agents/openai.yaml 263 B
- assets/templates/AGENTS-root.md 992 B
- assets/templates/AGENTS-source.md 500 B
- assets/templates/context-topic.md 494 B
- assets/templates/v-model/01-stakeholder-outcomes.md 475 B
- assets/templates/v-model/02-system-requirements.md 398 B
- assets/templates/v-model/03-subsystem-contracts.md 620 B
- assets/templates/v-model/04-component-contracts.md 493 B
- assets/templates/v-model/index.md 921 B
- assets/templates/v-model/verification.md 1.6 KB
- references/agent-context-documentation.md 4.2 KB
- references/discovery-and-interviews.md 6.2 KB
- references/repository-layout.md 4.8 KB
- references/review-and-compaction.md 4.9 KB
- references/subagent-playbooks.md 4.1 KB
- references/v-model-and-traceability.md 7.5 KB
- scripts/lint_repository_docs.py 66 KB runs code
- scripts/test_lint_repository_docs.py 11 KB runs code
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.
- 12d ago First seen · 116 lines · 89 tokens per session scan A 6c8795343dc1
document-repository-v-model is a skill published in the GitHub repository Krastanov/JuliaLLMAgentSkills (30 stars, last pushed 1mo ago), licensed Unlicense. It adds 89 tokens to every session and 1,238 once invoked, about $0.0004 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…