Borrowing it
Nothing to install: this file belongs to jyunming/Axon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jyunming/Axon/main/.github/instructions/reviewer.instructions.mdgit clone --depth 1 https://github.com/jyunming/AxonWrote 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/instructions/jyunming/axon/reviewer)<a href="https://agentmods.dev/instructions/jyunming/axon/reviewer"><img src="https://agentmods.dev/badge/instructions/jyunming/axon/reviewer/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/instructions/jyunming/axon/reviewer"><img src="https://agentmods.dev/badge/instructions/jyunming/axon/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00549 | $0.00549 |
| Opus 5.5 | $0.00220 | $0.00220 |
| Sonnet 5.5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
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 1mo 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 — 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 keysid,text,metadata. Missing keys will cause silent failures downstream. - Unique
idgeneration — 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
-
/ingestendpoint inapi.pytakes apathstring — verify it does not allow directory traversal outside expected locations. -
POST /add_textaccepts 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 (
HTTPExceptionwithdetailstring). - 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
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.
- 1mo ago First seen · 47 lines · 549 tokens per session scan A 912495267c35
Axon reviewer.instructions.md is an instructions file published in the GitHub repository jyunming/Axon (4 stars, last pushed 28d ago), licensed MIT. It adds 549 tokens to every session, about $0.0022 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.