agentmods.dev

Axon reviewer.instructions.md

Axon reviewer.instructions.md is an instructions file for GitHub Copilot from jyunming/Axon. It costs 549 tokens per session, scanned A, original, MIT.

A set of code-review instructions for the Axon repository. It tells a reviewer to focus on bugs, security weaknesses, and logic errors, including checks specific to Axon’s loaders, search index, API, and configuration.

In plain words
What is it for?
Use it to review changes to Axon loaders, configuration mapping, BM25 search storage, document ingestion, API endpoints, and security-sensitive code.
Why use it?
It gives reviews a consistent focus and helps catch failures that may otherwise be silent, such as duplicate document IDs or missing fields. It also calls out risks such as directory traversal and unsafe pickle use.

Instructions file for GitHub Copilot

not rated 5 today A scan 549 tokens original MIT
View the source file jyunming/Axon
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/reviewer
Clone the repo
git clone --depth 1 https://github.com/jyunming/Axon

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for Axon reviewer.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jyunming/axon/reviewer.svg)](https://agentmods.dev/instructions/jyunming/axon/reviewer)
Your own site
<a href="https://agentmods.dev/instructions/jyunming/axon/reviewer"><img src="https://agentmods.dev/badge/instructions/jyunming/axon/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 549 This file is loaded in full into every session.
When invoked 549 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 $0.00549 $0.00549
Opus 5 $0.00275 $0.00275
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 5d ago against content hash 912495267c35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Axon reviewer.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 5d 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/reviewer.instructions.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: Code Reviewer

You are a code reviewer for the Axon repository. You identify only issues that genuinely matter — bugs, security vulnerabilities, and logic errors. You do not comment on formatting, style, or personal preference.

Review Checklist — Axon Specific

Correctness

  • New loaders return List[Dict] with required keys id, text, metadata. Missing keys will cause silent failures downstream.
  • Unique id generation — duplicate IDs silently overwrite documents in ChromaDB.
  • AxonConfig.load() correctly maps new YAML keys to dataclass fields; missing mapping silently uses defaults.
  • BM25Retriever.add_documents() rebuilds the full index on every call (by design, not a bug) — flag if called in a hot loop.

Security

  • /ingest endpoint in api.py takes a path string — verify it does not allow directory traversal outside expected locations.
  • POST /add_text accepts arbitrary text — no injection risk if only stored and embedded, but flag if the text feeds a shell command.
  • BM25Retriever.load() now uses JSON (bm25_corpus.json); legacy pickle is migrated on first load — flag any new code that re-introduces pickle for index storage.
  • New dependencies — flag if they introduce network calls at import time or have known CVEs.

Performance

  • Embedding is batched in chunks of 32. New code that calls embed() in a loop without batching is a regression.
  • BM25 index is rebuilt synchronously on every add_documents() call. Flag if called during a request without a background task.

API Contracts

  • New FastAPI endpoints must return consistent error format (HTTPException with detail string).
  • New agent-facing endpoints must have a corresponding tool definition added to src/axon/tools.py.

What NOT to Comment On

  • Formatting, indentation, line length
  • Variable naming (unless genuinely confusing)
  • Code that is already working and not touched by this PR
  • Suggestions that are subjective improvements with no correctness impact

Read the full file on GitHub · 47 lines

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. 5d ago First seen · 47 lines · 549 tokens per session scan A 912495267c35

Subscribe to this mod's changes

Axon reviewer.instructions.md is an instructions file published in the GitHub repository jyunming/Axon (5 stars, last pushed today), licensed MIT. It adds 549 tokens to every session, about $0.0027 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.

Code reviewSecurityclaude-codeembeddingsfastapigraphraghybrid-searchknowledge-base
Related

Other instructions, from other repositories

OpenNotebookLM AGENTS.md

AGENTS.md instructions for tom1030507/OpenNotebookLM, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

tom1030507/OpenNotebookLM · 1,612 tokens

knowledge-base CLAUDE.md

Claude Code instructions for riemannulus/knowledge-base, covering knowledge-base 개발 가이드, 명령어, 아키텍처 (데이터 흐름), 깨뜨리기 쉬운 불변 원칙 and 확장 포인트.

riemannulus/knowledge-base · 3,335 tokens

fortemi CLAUDE.md

Claude Code instructions for Fortemi/fortemi, covering matric memory, ci/cd, gitea actions workflows, monitoring builds and check recent runs via mcp.

Fortemi/fortemi · 6,245 tokens

fortemi AGENTS.md

AGENTS.md instructions for Fortemi/fortemi, covering agents.md, framework context, tier 1 / tier 2 / tier 3 loading model, tier 2 capability map and agents.

Fortemi/fortemi · 1,723 tokens

RAG-In-A-Box AGENTS.md

AGENTS.md instructions for DevNexsler/RAG-In-A-Box, covering gitnexus — code intelligence, always do, never do, resources and cli.

DevNexsler/RAG-In-A-Box · 1,063 tokens

RAG-In-A-Box CLAUDE.md

Claude Code instructions for DevNexsler/RAG-In-A-Box, covering gitnexus — code intelligence, always do, never do, resources and cli.

DevNexsler/RAG-In-A-Box · 1,070 tokens