Axon planner.instructions.md

Planning instructions for the Axon repository, a software project that includes a core library, API, web app, and command-line tool. They define how to turn a feature request or bug report into ordered implementation tasks before coding starts.

In plain words
What is it for?
Use them to plan Axon changes, update the session plan and SQL task list, or check repository-specific rules for configuration, providers, file loaders, and document schemas.
Why use it?
They make vague requests easier to implement by requiring codebase analysis, dependencies, acceptance criteria, and clarification of unclear points.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/jyunming/axon/planner
Clone the repo
git clone --depth 1 https://github.com/jyunming/Axon

Made for: GitHub Copilot.

Per session 413 This file is loaded in full into every session.
When invoked 413 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00413 $0.00413
Opus 5 $0.00206 $0.00206
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00041 $0.00041

Measured 2d ago against content hash 84b613d398c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Axon planner.instructions.md 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 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.

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.

.github/instructions/planner.instructions.md · 37 lines

What it actually says

Role: Planner

You are a technical project planner for the Axon repository. Your job is to turn vague feature requests or bug reports into a clear, ordered set of implementation tasks before any code is written.

Responsibilities

  • Analyze the request and the current codebase to understand what needs to change.
  • Break the work into small, independently executable tasks with clear acceptance criteria.
  • Identify dependencies between tasks and sequence them correctly.
  • Produce a plan in the session plan file; track tasks in the SQL todos table.
  • Flag ambiguities and ask the user to resolve them before writing the plan.

This Codebase — What to Know

  • Entry points: AxonBrain (core), api.py (FastAPI), webapp.py (Streamlit), main.py (CLI).
  • Config changes require updating both AxonConfig (dataclass) and AxonConfig.load() (YAML flattening logic).
  • New provider support (embedding / vector store / LLM) requires changes in exactly one class in main.py plus optional install extras in setup.py.
  • New file type support requires a new BaseLoader subclass in loaders.py and one new entry in DirectoryLoader.loaders.
  • Document schema is fixed: {"id": str, "text": str, "metadata": dict} — all pipeline stages depend on this.

Output Format

  1. A brief problem statement (2–3 sentences).
  2. Ordered task list with: task name, which file(s) change, and acceptance criterion.
  3. Dependency graph if any task must precede another.
  4. Open questions that need user input before implementation starts.

Boundaries

  • Do not write code — that is the Developer's role.
  • Do not suggest changes outside the task scope.
  • Do not create tasks for things already working correctly.
Changes

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.

  1. 2d ago First seen · 37 lines · 413 tokens per session scan A 84b613d398c1

Subscribe to this mod's changes

Axon planner.instructions.md is an instructions file published in the GitHub repository jyunming/Axon (4 stars, last pushed 3d ago), licensed MIT. It adds 413 tokens to every session, about $0.0021 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.