Borrowing it
Nothing to install: this file belongs to jarmak-personal/hvir. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jarmak-personal/hvir/main/.claude/skills/hvir-implement-epic/SKILL.mdgit clone --depth 1 https://github.com/jarmak-personal/hvirWrote 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/jarmak-personal/hvir/hvir-implement-epic)<a href="https://agentmods.dev/skills/jarmak-personal/hvir/hvir-implement-epic"><img src="https://agentmods.dev/badge/skills/jarmak-personal/hvir/hvir-implement-epic/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/jarmak-personal/hvir/hvir-implement-epic"><img src="https://agentmods.dev/badge/skills/jarmak-personal/hvir/hvir-implement-epic.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 | $0.00064 | $0.02477 |
| Opus 5 | $0.00032 | $0.01239 |
| Sonnet 5 | $0.00013 | $0.00495 |
| Haiku 4.5 | $0.00006 | $0.00248 |
Grade A, and why
hvir-implement-epic 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 3d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement an hvir epic
Act as the private epic coordinator: staff TPM and system architect for one authorized epic. Own scheduling, cross-child coherence, review selection, integration, cumulative delivery, and exact cleanup. Do not implement or patch child feature code. Keep the dependency graph, scheduling notes, agent messages, and review transcripts inside the agent run; GitHub receives only curated issues, focused pull requests, required relationships, lifecycle results, and maintainer-facing summaries.
This skill starts only when a maintainer invokes it to coordinate an aligned epic and its direct
children. A later explicitly resumed invocation may perform bounded post-merge cleanup, but final
pull-request acceptance remains the small GitHub-owned workflow in hvir-merge-pr.
Establish authority and scope
Read AGENTS.md, CONTRIBUTING.md, docs/design.md, the relevant ADRs, the epic, and every
proposed direct child before changing Git or launching a child. Use the repository and Project
interfaces from docs/project-management.md to confirm:
- one aligned, open issue with exactly one
kind:epiclabel; - its native direct children and their current open/closed and Project states;
- the exact child set the maintainer authorized for this run; and
- no nested epic, cross-repository child, materially changed outcome, or unresolved product or architecture decision.
Treat an explicit invocation for the epic as authorization for its current direct child set only when that set is unambiguous in the aligned epic record. Ask the maintainer to confirm any ambiguous or changed set. New scope and materially changed child outcomes require issue alignment and fresh authorization. Do not post routine coordination updates to GitHub.
Establish the epic branch
Supply credentials only through the environment documented in docs/project-management.md.
Fetch and prune remote refs, inspect local and remote epic/<epic-number>-* refs, and inspect
registered worktrees before selecting anything. Preserve the invoking checkout's branch and
working state; perform epic work only in the deterministic epic worktree.
What ships with it
1 file 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.
- 3d ago Changed · -26 lines 8e90d0483d20
- 12d ago First seen · 230 lines · 64 tokens per session scan A bd8aee3d717b
hvir-implement-epic is a skill published in the GitHub repository jarmak-personal/hvir (2 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 2,477 once invoked, about $0.0003 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 2026-08-31.
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…
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…
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…
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…