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 instructions/jerrinot/ap-query/agents-mdgit clone --depth 1 https://github.com/jerrinot/ap-queryWhat 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 | $0.00835 | $0.00835 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
ap-query AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Purpose & Agent Output
ap-queryis built for LLM agents analyzing async-profiler recordings.- Keep outputs compact and directly actionable to avoid wasting tokens.
- Use concise plain text in terminal workflows.
- Never use JSON for agent-facing guidance, examples, or command output formatting in this repository.
- Plain text is required because LLM agents parse it well and it is more concise.
Project Structure & Module Organization
- The repository is a single Go CLI module (
go.mod) with command dispatch inmain.go. - Commands are split into root-level files like
hot.go,tree.go,diff.go,events.go, andinit.go. - Tests live primarily in
main_test.go; profiling fixtures are intestdata/(*.jfr,*.jfr.gz). - Fixture generation utilities are under
testdata/gen/(generate.sh,Workload.java). - CI and release automation are defined in
.github/workflows/and.goreleaser.yml.
Build, Test, and Development Commands
go build -o ap-query .builds the local binary.go test -v ./...runs the full test suite.go test -run TestName -vruns a targeted test while iterating.echo "A;B;C 10" | ./ap-query hot -runs a quick smoke check for collapsed-stack input../testdata/gen/generate.sh /path/to/libasyncProfiler.soregenerates JFR fixtures (Java 17+ and async-profiler required).
Code Quality
- Never apply hacks, workarounds, or dirty fixes. Find and fix the root cause.
- If something is a bug, treat it as a bug regardless of how unlikely it is.
- Don't be lazy or sloppy. There is no deadline — take all the time and tokens needed for a proper solution.
- During reviews, act on dead code, unreachable branches, stale comments, and unused imports — don't just note them. Tidy up even when it's not a functional bug.
Coding Style & Naming Conventions
- Follow idiomatic Go formatting and structure; run
gofmtbefore committing. - Use tabs/standard Go formatting and keep functions small and command-focused.
- Keep file names lowercase and command-oriented (
callers.go,lines.go,filter.go). - Prefer clear lowerCamelCase helper names and concise error messages.
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.
- 2d ago First seen · 54 lines · 835 tokens per session scan A 1dd3c0f61aac
ap-query AGENTS.md is an instructions file published in the GitHub repository jerrinot/ap-query (10 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 835 tokens to every session, about $0.0042 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 instructions, from other repositories
mcp-jperf AGENTS.md
AGENTS.md instructions for theSharque/mcp-jperf, covering agents.md, cursor cloud specific instructions, development commands, testing the mcp server and runtime dependency.
uniprof CLAUDE.md
Instructions for indragiek/uniprof, covering uniprof codebase guide, project layout, quick start, cli reference and aliases & parsing.
uniprof AGENTS.md
Instructions for indragiek/uniprof, a project described as: Universal CPU profiler designed for humans and AI agents.
imgui-java CLAUDE.md
Instructions for SpaiR/imgui-java: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
toBeBetterJavaer AGENTS.md
AGENTS.md instructions for itwanger/toBeBetterJavaer, covering 工具权限设置, 工具使用规则, 获取网页内容 and 图片生成 / 文章配图.
Sighthound AGENTS.md
Instructions for Corgea/Sighthound, covering claude, commands, python / django test naming and agent skill.