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/itsasheruwu/veo/agents-mdgit clone --depth 1 https://github.com/itsasheruwu/VeoWhat 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 | $0.03882 | $0.03882 |
| Opus 5 | $0.01941 | $0.01941 |
| Sonnet 5 | $0.00776 | $0.00776 |
| Haiku 4.5 | $0.00388 | $0.00388 |
Grade B, and why
Veo AGENTS.md scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Mechanics: gpt-5.6-sol is only reachable through the Codex CLI — `codex exec` / `codex review` (my `~/.codex/config.toml` defaults to gpt-5.6-sol). Use the codex-implementation, codex-review, and codex-computer-use ski How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Veo Repository Guide
Veo is a local-first native macOS workspace for the Codex CLI. The repository contains one Mac app, one direct local app-server transport, and no hosted product or mobile companion.
Do not add a mobile companion, relay, phone pairing, subscriptions, hosted deployment, or compatibility layers for an earlier product architecture. Keep code, documentation, automation, assets, and product copy specific to Veo.
Core guardrails
- Prefer the native Mac app, direct local
codex app-servertransport, local project folders, and normal macOS window/menu workflows. - Be an intraprendente agent: proactively inspect local code, protocol/schema, and official sources to confirm facts before replying; do not repeatedly stop to ask for confirmation when the next verification step is safe and obvious.
- Keep repo isolation by thread/project metadata and local
cwd. - Do not reintroduce filtering by selected repo in sidebar/content.
- Keep cross-repo open/create flow with automatic local context switch.
- Preserve single responsibility: shared logic belongs in services/coordinators, not duplicated in views.
- Treat this repo as open source: avoid junk code, placeholder hacks, noisy one-off workarounds, and low-signal docs.
- Keep public documentation centered on Veo's current Mac app, actual source layout, direct local transport, and explicit access model.
- Do not create one-off report markdown files in the repo root (security reports, audit notes, scratch summaries, etc.) unless the user explicitly asks for a file. Keep ad-hoc analysis in the chat.
- Keep user-facing answers compact by default unless the user explicitly asks for more detail.
macOS runtime + timeline guardrails
turn/startedmay not include a usableturnId: keep the per-thread running fallback.- If Stop is tapped and
activeTurnIdByThreadis missing, resolve viathread/readbefore interrupting. - On process reconnect or app relaunch, rehydrate the selected thread and active turn state so Stop remains visible.
- Treat
codex app-serverstdout as newline-delimited JSON-RPC only; keep diagnostics on stderr and never mix them into protocol parsing. - Keep assistant rows item-scoped to avoid timeline flattening/reordering.
- Merge late reasoning deltas into existing rows; do not spawn fake extra "Thinking..." rows.
- Ignore late turn-less activity events when the turn is already inactive.
- Preserve item-aware history reconciliation instead of falling back to
turnId-only matching.
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.
- 2d ago First seen · 168 lines · 3,882 tokens per session scan B f516ba462320
Veo AGENTS.md is an instructions file published in the GitHub repository itsasheruwu/Veo (1 stars, last pushed 13d ago), licensed Apache-2.0. It adds 3,882 tokens to every session, about $0.0194 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
modeldeck CLAUDE.md
Claude Code instructions for timharris707/modeldeck, covering modeldeck — repo agent context, never compromise and team-workflow pack.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
personal-model AGENTS.md
Instructions for Intuition-Lab/personal-model, covering agents.md, runtime boundary, commands, pipeline and documentation map.
humla CLAUDE.md
Instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.
os-clovy AGENTS.md
Instructions for open-software-network/os-clovy, covering clovy — agent instructions, project, os platform (shared brain), structure and domain & decisions — read before writing code.
humla AGENTS.md
Instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.