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 commands/luccapinto/agentic-data-kit/plangit clone --depth 1 https://github.com/luccapinto/agentic-data-kitWhat 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 | $0.00019 | $0.00256 |
| Opus 5 | $0.00010 | $0.00128 |
| Sonnet 5 | $0.00004 | $0.00051 |
| Haiku 4.5 | $0.00002 | $0.00026 |
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 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.
What it actually says
Workflow: /plan
Usage: /plan <what you want to build>
Produce a written plan before any implementation. This command writes a plan file and stops — it does not write code.
Steps
- Understand. Read the relevant parts of the repo. If a key requirement is genuinely ambiguous, ask; otherwise state your assumptions.
- Route. Identify which agent(s) own each part of the work (e.g.
data-engineerfor the pipeline,analytics-engineerfor the model,powerbi-developerfor the dashboard). - Write the plan to
docs/PLAN-<slug>.md, where<slug>is 2–3 hyphenated keywords from the request. Include:- Goal & scope (and explicit non-goals).
- Task breakdown with the responsible agent per task.
- Dependencies & risks.
- Verification checklist (how we'll know it works).
- Report the exact file path created and suggest reviewing it before implementing.
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 · 26 lines · 19 tokens per session scan A ced9c0900801
plan is a command published in the GitHub repository luccapinto/agentic-data-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 256 once invoked, about $0.0001 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 commands, from other repositories
test-discovery
Discover and write missing tests for altimate-code. Runs hourly to find real-world gaps. Uses a team with a critic to validate tests before committing.
sdd-setup
Onboarding wizard — DocLanguage, Memory Bank, architecture snapshot, working agreements (quality gate, TDD working mode).
choose-model
Compare current models across configured AI providers and produce an executable plan without running paid work. Use when the user asks which model or provider should perform a task.
setup
Check whether GitHub Copilot CLI is installed, authenticated, and ready for delegation.
review
Review code across five axes with categorized findings.
maintenance
Run routine maintenance on the AI knowledge base system.