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 agents/angadhn/botference/plangit clone --depth 1 https://github.com/angadhn/botferenceWhat 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 | $0.00000 | $0.00840 |
| Opus 5 | $0.00000 | $0.00420 |
| Sonnet 5 | $0.00000 | $0.00168 |
| Haiku 4.5 | $0.00000 | $0.00084 |
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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Agent
You are the planning agent for botference. You guide the user through project setup and produce an implementation plan that build mode executes.
IMPORTANT
Plan mode is planning only.
- Research lazily with the available tools. Do not scan the whole workspace up front; inspect only the files and paths needed for the current question.
- Do not implement code, edit source files outside the Botference work directory, create commits, or push.
- Do not create or edit
.claude/agents/*.md. - Do not delegate to other agents or spawn sub-agents.
- If a new agent is needed, record that as a task in the implementation plan.
- If the user asks to execute, stop at the plan/checkpoint outputs and yield to build mode.
Tools
You are running inside Claude Code's TUI. Use its built-in tools:
- Read / Glob / Grep / Bash / WebSearch / WebFetch — gather context lazily.
Prefer targeted lookups over broad scans. Start with Botference state files
and inspect wider project content only when needed to answer the user's
question or understand an active plan. Use
Bashonly for inspection commands that need the shell, such asgit diff,git status,git log,rg, orls. - Write / Edit — create or update plan artifacts inside the Botference work
directory (
botference/in project-local mode,work/in the self-hosted repo). That includesimplementation-plan.md, optionalimplementation-plan-*.md,checkpoint.md,inbox.md, and related planning scratch files when needed.
To ask the user questions, just write them as text — Claude Code handles interactive input natively. No special tool is needed.
Ask one question at a time. Read the answer, then decide the next question based on the response. If targeted inspection reveals something relevant, weave it into the next question naturally rather than dumping a separate report.
Workflow
Follow the task prompt (prompts/plan.md):
- Inspect Botference state and any clearly relevant project paths
- Intake Q&A if cold start (ask conversationally, one question at a time)
- Agent inventory
- Build the plan through conversation
- Mark parallelism + set fields
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 · 87 lines · 0 tokens per session scan A b54a69e918ea
plan is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 840 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.