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/mnapoli/phpstorm-prereview/agents-mdgit clone --depth 1 https://github.com/mnapoli/phpstorm-prereviewWhat 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 | $0.00556 | $0.00556 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
phpstorm-prereview 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prereview — development notes
PhpStorm plugin for local, PR-style code review: inline comments in the editor, written by the user or imported from AI agent runs (codex and claude CLIs reviewing the current branch against the default branch).
Build & run
./gradlew build— compile + tests./gradlew runIde— sandboxed PhpStorm with the plugin- The Gradle wrapper defaults
GRADLE_USER_HOMEto./.gradle-user-home(unless already set) to isolate plugin-SDK caches. - Releases are driven by GitHub releases: the tag
vX.Y.Zbecomes the plugin version;pluginVersioningradle.propertiesis only a local fallback.
Architecture decisions
- The core UI primitive is a component inlay card (a real Swing panel embedded in the editor via
ComponentInlayAdapter), not a gutter-icon-plus-tool-window combo. The quality of the inline UX is the whole point of the plugin; prefer improving the card over adding secondary surfaces. - Comment display has two states: compact (range highlight + gutter marker) and expanded (the inlay card). The tool window is a fallback/overview, not the primary surface.
- Anchoring is deliberately best-effort: file URL + offsets + line, plus a dedicated anchor line (card renders under the end of the selection) and a small context snippet. Anchors track document edits (
ReviewCommentDocumentSyncService) and file renames/moves (ReviewCommentsVfsSyncService); imprecision after heavy refactors is accepted, don't over-engineer recovery. - Persistence is project-local via
PersistentStateComponent(ReviewCommentsServiceis the source of truth). No remote sync by design. - Agent runs (
AgentReviewService) execute thecodexandclaudeCLIs in parallel throughStructuredCliReviewRunnersubclasses, with a JSON output schema. Each agent's comments replace that agent's previous comments only when its run succeeds. CLI binaries are auto-discovered inPATHand common install locations — no user configuration.
Non-goals
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 · 32 lines · 556 tokens per session scan A e428771279b8
phpstorm-prereview AGENTS.md is an instructions file published in the GitHub repository mnapoli/phpstorm-prereview (11 stars, last pushed 22d ago), licensed MIT. It adds 556 tokens to every session, about $0.0028 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 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.