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/AGENTS.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/instructions/jarmak-personal/hvir/agents-md)<a href="https://agentmods.dev/instructions/jarmak-personal/hvir/agents-md"><img src="https://agentmods.dev/badge/instructions/jarmak-personal/hvir/agents-md/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/instructions/jarmak-personal/hvir/agents-md"><img src="https://agentmods.dev/badge/instructions/jarmak-personal/hvir/agents-md.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 | $0.01756 | $0.01756 |
| Opus 5.5 | $0.00702 | $0.00702 |
| Sonnet 5.5 | $0.00351 | $0.00351 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
hvir AGENTS.md 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 4d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in this repository.
What is hvir?
hvir = Harness · View · Interact · Respond.
A lightweight, view-first workbench for agentic development: a beautiful code + git explorer wrapped around the terminals (harnesses like Claude Code / Codex) you actually like. It is not an IDE and not an editor — it's a viewer, tuned for the "I hand off to agents frequently but stay in the loop" workflow.
The name is the thesis: watch the harness, view the codebase/git, interact lightly, respond. VSCode is more than we want; tmux is too hands-off. hvir sits between them.
Read docs/design.md before doing substantive work — it holds the
product philosophy, guardrails, architecture, risk posture, and the linked ADR index.
Start with the index's read-first constraints, then
read the relevant feature decisions under docs/adr/. Follow lifecycle
notices and replacement scopes: partial supersession leaves unaffected rules authoritative.
Implementation and acceptance work is tracked in GitHub issues, commits, and pull
requests. Do not add progress checklists, status logs, or test-run evidence to ADRs.
docs/plan/ is frozen historical implementation context, not
an active tracker; do not update its checkboxes or status tables to record new work.
Start substantive implementation from a governing GitHub issue. Align on the problem,
product fit, architecture questions, and acceptance there before editing. A PR to main uses
Closes #N; an epic-child PR uses the exact contribution relationships documented in
CONTRIBUTING.md. Broad epics should be decomposed into independently
reviewable child issues.
Final acceptance is separately authorized. hvir-implement-issue and
hvir-implement-epic stop at verified, pushed pull-request handoffs. A maintainer invokes
hvir-merge-pr to approve one final pull request; an explicit pull-request number wins, while an
omitted number may reuse only one pull request from the latest verified lifecycle handoff in the
active interaction. The skill requests GitHub's protected merge directly, then uses the focused
Project owners to converge the native closing issue. Epic-child integration remains owned by
hvir-implement-epic; ordinary and cumulative final pull requests share the small acceptance
path.
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.
- 4d ago Changed · +4 lines · +87 tokens per session 7f556ed7a6bf
- 1mo ago Changed · +2 lines · +37 tokens per session 769a14f6c732
- 1mo ago First seen · 111 lines · 1,632 tokens per session scan A 1a4891324ec2
hvir AGENTS.md is an instructions file published in the GitHub repository jarmak-personal/hvir (3 stars, last pushed today), licensed MIT. It adds 1,756 tokens to every session, about $0.0070 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.