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 skills/zayeagle/omnidev-kit/odnpx skills add zayeagle/omnidev-kit --skill odgit clone --depth 1 https://github.com/zayeagle/omnidev-kitWrote 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/zayeagle/omnidev-kit/od)<a href="https://agentmods.dev/skills/zayeagle/omnidev-kit/od"><img src="https://agentmods.dev/badge/skills/zayeagle/omnidev-kit/od.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 | $0.00088 | $0.06974 |
| Opus 5 | $0.00044 | $0.03487 |
| Sonnet 5 | $0.00018 | $0.01395 |
| Haiku 4.5 | $0.00009 | $0.00697 |
Grade B, and why
od 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| **Codex** | **`request_user_input` tool — REQUIRED same turn** in **Plan AND Default/Code mode**. Copy-paste JSON from interactive-prompt.md **§6**. Enable Default mode: `[features] default_mode_request_user_input = tr How it starts
The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OmniDev Workflow Skill
Single source of truth for OmniDev rules. Applies ONLY when trigger-gate activates (Signal A).
A. Command Reference
→ Full reference in engine/commands.md. Load only on /od h or /od help.
B. Core Rules
B.0 — When unsure, ask; do not invent
Highest priority: Any uncertainty / ambiguity / guess → stop and confirm. Destructive actions (delete, deploy, etc.) default to "do not execute".
→ Full rules: engine/context-lifecycle.md §1 · engine/interactive-prompt.md §3.4 b0_confirm
B.1 — Trigger & Activation
Activate only on Signal A (/od or $od line-start prefix) or Signal A-index (bare 1–9 when session-log has pending_decision). Attaching @od / invoking the skill without that prefix does not start the workflow (reference only). Phases 0–5 in order; /od re/$od re resume from disk; bare n/continue do not trigger (may show a one-line tip). Index pick: /od 1 or bare 1 with pending — see interactive-prompt §8.1.
→ engine/trigger-gate.md · engine/activation.md
B.4 — Interactive Prompt (primary working mode)
interactive_mode: true is on by default. At decision points must call the native tool first, same turn as the summary; prose-only is forbidden. Keep short chat summaries (Phase 0 ≤6 lines); forbid od_interactive metadata in chat. On native failure → §8 Markdown /od table + write pending_decision. User may reply /od N or bare N (with pending). Hard ban: box-drawing / || / +--+ / pad-aligned "fake modal" frames. Always STOP — WAIT.
→ engine/interactive-prompt.md
B.11 — Session Resume
/od re or $od re resumes from session-log.md YAML frontmatter; with payload continues changes; /od x saves and exits. Do not infer from chat context.
→ engine/session-memory.md
What ships with it
28 files 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.
- engine/activation.md 9.0 KB
- engine/board.md 12 KB
- engine/commands.md 9.2 KB
- engine/context-lifecycle.md 5.2 KB
- engine/document-history.md 7.1 KB
- engine/evolution.md 4.0 KB
- engine/governance.md 2.0 KB
- engine/interactive-prompt.md 15 KB
- engine/metrics.md 4.1 KB
- engine/multi-agent-architecture.md 7.5 KB
- engine/security-audit.md 6.6 KB
- engine/session-memory.md 14 KB
- engine/skill-composition.md 7.0 KB
- engine/special-flows.md 14 KB
- engine/stash.md 4.9 KB
- engine/test-strategy.md 11 KB
- engine/token-optimization.md 7.1 KB
- engine/trigger-gate.md 6.9 KB
- engine/user-preferences.md 3.7 KB
- phases/00-assessment.md 6.4 KB
- phases/01-blueprint.md 6.2 KB
- phases/02-planning.md 7.0 KB
- phases/03-development.md 6.4 KB
- phases/04-testing.md 11 KB
- phases/05-deploy.md 14 KB
- templates/board.canvas.tsx 5.2 KB
- templates/flow-board.json 262 B
- templates/flow-board.md 943 B
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 First seen · 387 lines · 88 tokens per session scan B 13e8d2bdae16
od is a skill published in the GitHub repository zayeagle/omnidev-kit (5 stars, last pushed 16d ago), licensed MIT. It adds 88 tokens to every session and 6,974 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…