heap-seance: Instructions file for Claude Code

CLAUDE.md

heap-seance CLAUDE.md is an instructions file for Claude Code from SegfaultSorcerer/heap-seance. It costs 267 tokens per session, scanned A, original, Apache-2.0.

Project instructions for investigating suspected Java memory leaks, where a program keeps using more memory over time.

In plain words
What is it for?
Use them to inspect a process, compare three memory snapshots, check garbage collection, and produce a confidence-rated diagnosis with next steps.
Why use it?
They provide cautious evidence rules so normal memory growth is not mistaken for a leak and serious investigations are supported by data.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is SegfaultSorcerer/heap-seance's own configuration. It tells Claude Code how to work on heap-seance itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything heap-seance configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SegfaultSorcerer/heap-seance. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SegfaultSorcerer/heap-seance/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SegfaultSorcerer/heap-seance

Made for: Claude Code.

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 heap-seance CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/segfaultsorcerer/heap-seance/claude-md/github.svg)](https://agentmods.dev/instructions/segfaultsorcerer/heap-seance/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/segfaultsorcerer/heap-seance/claude-md"><img src="https://agentmods.dev/badge/instructions/segfaultsorcerer/heap-seance/claude-md/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.

agentmods 80×15 button for heap-seance CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/segfaultsorcerer/heap-seance/claude-md"><img src="https://agentmods.dev/badge/instructions/segfaultsorcerer/heap-seance/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 267 This file is loaded in full into every session.
When invoked 267 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00267 $0.00267
Opus 5 $0.00133 $0.00133
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00027 $0.00027

Measured 9d ago against content hash 7f59bfaca97e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

heap-seance CLAUDE.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 9d 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.

CLAUDE.md · 37 lines

What it actually says

Heap Seance Project Instructions

Use this project to diagnose Java memory leaks with low false-positive bias.

Default policy

  • Prefer conservative decisions.
  • Run deep forensics only when both signals are present:
    • monotonic class growth across 3 histogram samples
    • old-gen pressure despite Full GC

Workflow

  1. Resolve target process (PID or process pattern).
  2. Collect 3 class histograms over time.
  3. Collect GC snapshot.
  4. Trigger deep forensics when thresholds are met:
    • JFR recording + summary
    • heap dump
    • MAT leak suspects
    • async-profiler allocation profile (optional tie-breaker)
  5. Return a structured report with confidence and remediation next steps.

Output format requirements

Always include:

  • verdict (probable_memory_leak, suspicious_growth, watch, no_strong_leak_signal)
  • confidence (none, low, medium, high)
  • key evidence bullets
  • next steps

Tooling constraints

  • If MAT is missing and deep forensics is required, fail explicitly and provide recovery instructions.
  • If async-profiler is missing, continue with JFR + MAT fallback and document reduced evidence depth.
  • Do not claim high confidence without evidence from at least two independent signals.
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. 9d ago First seen · 37 lines · 267 tokens per session scan A 7f59bfaca97e

Subscribe to this mod's changes

heap-seance CLAUDE.md is an instructions file published in the GitHub repository SegfaultSorcerer/heap-seance (4 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 267 tokens to every session, about $0.0013 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens