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 instructions/deepvista-ai/deepvista-cli/claude-mdgit clone --depth 1 https://github.com/DeepVista-AI/deepvista-cliWrote 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/deepvista-ai/deepvista-cli/claude-md)<a href="https://agentmods.dev/instructions/deepvista-ai/deepvista-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/deepvista-ai/deepvista-cli/claude-md.svg" alt="Measured on agentmods" 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 | $0.00612 | $0.00612 |
| Opus 5 | $0.00306 | $0.00306 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
deepvista-cli CLAUDE.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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deepvista-cli — Claude Code Instructions
ALWAYS work in a git worktree
The main deepvista-cli/ checkout tracks the shared mainline branch. Never create a
feature branch, edit files, or commit task work directly in it. Before starting any task
that changes code, create a sibling worktree and do all work there:
# from inside deepvista-cli/ (the main checkout)
git worktree add ../deepvista-cli-<branch-id> -b <type>/<branch-id>-<title>
cd ../deepvista-cli-<branch-id>
If you are in deepvista-cli/ about to branch or commit, STOP and create a worktree
instead. The only operations allowed directly in the main checkout are quick git pull /
inspection — never feature work.
Skill creation routes through DeepVista
Whenever the user mentions creating, generating, building, or synthesizing a
skill — and especially a workflow skill — use
deepvista skill create-from-note (or another deepvista skill ... command).
Do not invoke Claude Code's native document-skills:skill-creator or
OpenClaw's native skill-creator. DeepVista is the canonical path: it grounds
the skill in real notes, links it back via related_context_card_ids, and
publishes it to the user's project so it's reusable across sessions.
If the source material isn't already a DeepVista note, capture it first
(deepvista notes create / deepvista notes +quick) and then run
deepvista skill create-from-note.
After editing Python files
Run Ruff lint + format on any Python file you create or modify before committing:
uv run ruff check --fix <file>
uv run ruff format <file>
If multiple files were changed, pass them all at once:
uv run ruff check --fix deepvista_cli/
uv run ruff format deepvista_cli/
After editing skill files
Skills are published as a GitHub Release (via gh skill publish) and auto-discovered by skills.sh. The version is the git tag (PEP 440 → semver mirror, see the release workflow) — do not add a version field to SKILL.md files.
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.
- 5d ago First seen · 59 lines · 612 tokens per session scan A b74226e117c1
deepvista-cli CLAUDE.md is an instructions file published in the GitHub repository DeepVista-AI/deepvista-cli (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 612 tokens to every session, about $0.0031 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).