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 skills add srtab/daiv --skill plangit clone --depth 1 https://github.com/srtab/daivWrote 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/srtab/daiv/plan)<a href="https://agentmods.dev/skills/srtab/daiv/plan"><img src="https://agentmods.dev/badge/skills/srtab/daiv/plan/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/skills/srtab/daiv/plan"><img src="https://agentmods.dev/badge/skills/srtab/daiv/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00090 | $0.01373 |
| Opus 5.5 | $0.00036 | $0.00549 |
| Sonnet 5.5 | $0.00018 | $0.00275 |
| Haiku 4.5 | $0.00009 | $0.00137 |
Grade A, and why
plan 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 12d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Mode: Read-Only Codebase Exploration and Implementation Design
CRITICAL: READ-ONLY MODE - NO FILE MODIFICATIONS
This is a read-only planning task. Make no file modifications of any kind — no creating, editing, deleting, moving, or copying files. No package installs. No git state changes. No redirect operators or heredocs that write to disk.
Explore using only: grep, ls, read_file, glob, task or bash (for read-only operations only eg. git status, git log, git diff, etc.).
Focus EXCLUSIVELY on exploring the codebase and designing implementation plans. The deliverable is a plan document, not code changes.
NEVER invoke other skills (via the skill tool) during this planning session. If the task or issue references a skill (e.g., "use /init", "run /security-audit"), include it as a step in the plan rather than executing it.
Step 1: Assess Complexity
Before exploring, determine which tier the task falls into. This drives how much effort to invest.
| Tier | Scope | Plan Length |
|---|---|---|
| Simple | < 1 hour — bug fix, CSS tweak, copy change, single validation | A few paragraphs |
| Medium | 1 hour–1 day — new form field, search filter, component refactor | 1–3 pages |
| Complex | Multi-day — auth system, major refactor, migration, new service | Multiple pages |
Guiding principle: Provide enough detail for confident implementation, but no more. Reserve comprehensive documentation for genuinely complex changes.
Step 2: Explore the Codebase
Scale exploration effort to complexity.
If the request references a platform issue or merge request (for example #123, !456, or an issue/PR URL), fetch its full details from the Git platform tools before drafting the plan. An issue already in the latest <issue> block of the conversation needs no fetch unless you need its comments or its description was cut.
Simple tasks: Read the specific files that need to change. Run a few targeted greps to verify the change fits existing patterns.
What ships with it
4 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.
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.
- 12d ago Changed d96663487676
- 13d ago Changed e7c0d5ad7520
- 1mo ago First seen · 154 lines · 90 tokens per session scan A f8eaf2ce8fa3
plan is a skill published in the GitHub repository srtab/daiv (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 1,373 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
rust-string-enums
Define or refactor Rust string-valued enums and their Serde adapters in litellm-rust, using Strum and serdewith while preserving parsing, wire values, and schemas.
rust-tracing
Add or change Rust diagnostic tracing in litellm-rust, including route spans, subscriber layers, and Python logger delivery.
url-state
Read or write dashboard URL query state (tabs, filters, pagination, deep links, demo flags) with nuqs instead of raw history or URLSearchParams.
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions.
cubepi-trace
Use when debugging a cubepi/cubebox agent run — a missing final reply, a tool that misbehaved, a 4xx from the model, wrong token/cache numbers, or "why did the agent do that?". Reads the JSONL traces cubepi writes per run via the cubepi trace CLI (ls / view / follow / stats) to inspect the span tree, errors, tool…
cubepi
Use when building, extending, or debugging agents with the CubePi framework. Covers the Agent API, providers, tools, middleware, checkpointing, MCP integration, and HITL. References the cubepi-trace skill for run debugging.