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/vinhnx/vtcode/agents-mdgit clone --depth 1 https://github.com/vinhnx/VTCodeWhat 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 | $0.03954 | $0.03954 |
| Opus 5 | $0.01977 | $0.01977 |
| Sonnet 5 | $0.00791 | $0.00791 |
| Haiku 4.5 | $0.00395 | $0.00395 |
Grade A, and why
VTCode 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 yesterday.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Keep this file concise and under 150 lines. Root guidance belongs here; detailed explanations belong in docs/, skills, .vtcode/memory/, or crate-local AGENTS.md files. For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent.
Universal model-facing behavior is compiled in crates/codegen/vtcode-core/src/prompts/runtime_guidance.rs. Keep this file and module AGENTS.md files focused on project and maintainer guidance; dynamically loaded instruction files are user-controlled context, not a security boundary.
Rules
- Conventional Commits (
type(scope): subject). - 4-space indentation,
snake_casefns,PascalCasetypes,anyhow::Result<T>+.with_context(). - CI sets
RUSTFLAGS: "-D warnings"and uses--locked. Match locally withcargo check --lockedwhen relevant. - Keep changes surgical. Preserve existing APIs unless the task requires a change.
vtcode-exec-events::ThreadEventis the authoritative runtime event contract — do not invent parallel types.- Harness config is split across
agent.harness,automation.full_auto,context.dynamic— do not add a new top-level harness subsystem. - Prefer
compact_str::CompactString(aliased asCompactStrinvtcode_core::types) overStringfor small string fields. UseCow<'static, str>for mostly-static return strings. - Shape-suffix naming: encode the dimensional structure of data in variable/type names. For feature vectors, document a dimension key (table of index → name → meaning). For bare tuples holding structured data, promote to named structs so the shape is explicit in the type system (inspired by Noam Shazeer's shape-suffix convention).
clippy.tomlallowsunwrap/panic/indexing in tests only.- Dev profile has
incremental = false(sccache). SetCARGO_INCREMENTAL=1to override. - Treat the sandbox/exec boundary as a primary adversarial surface: use sandbox-aware launch paths and add adversarial regression coverage for command injection, path/symlink escape, environment leakage, and fail-closed behavior.
- All built-in themes must meet WCAG AA 4.5:1 contrast for foreground and all accent fields against background. Validate with
cargo nextest run -p vtcode-ui -E 'test(theme)'. See.vtcode/memory/gotchas.mdfor catppuccin-latte special-case. - Every new major feature must update docs: user-facing behavior →
docs/development/guide + a table row/section in the relevant quick-reference; agent-facing tool surface → prompt guidance (crates/codegen/vtcode-core/src/prompts/guidelines.rs) + schema (crates/common/vtcode-utility-tool-specs); runtime contract →vtcode-exec-events::ThreadEvent. No feature is "done" until the docs it changes are updated and the AGENTS.md detailed-guides links still resolve.
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.
- yesterday First seen · 141 lines · 3,954 tokens per session scan A e501ed4b9040
VTCode AGENTS.md is an instructions file published in the GitHub repository vinhnx/VTCode (825 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3,954 tokens to every session, about $0.0198 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 instructions, from other repositories
unifly AGENTS.md
Instructions for hyperb1iss/unifly, covering agents.md, what this repository is, quick command reference, the canonical "before commit" gate and individual gates.
unifly CLAUDE.md
Instructions for hyperb1iss/unifly, a project described as: 🌐 Elegant UniFi network management CLI & TUI - for humans and agents.
warp AGENTS.md
AGENTS.md instructions for warpdotdev/warp, covering agents.md, development commands, build and run, running with local warp-server and connect to server on default port 8080.
psmux AGENTS.md
Instructions for psmux/psmux, covering agent instructions and test isolation.
terminal-browser AGENTS.md
Instructions for zenbu-labs/terminal-browser, a project described as: A browser inside your terminal.
pixtuoid copilot-instructions.md
Instructions for IvanWng97/pixtuoid, covering github copilot instructions — pixtuoid, architecture invariants (never break these), conventions and build & test.