harness-binary-spelunking

harness-binary-spelunking is a skill for Claude Code, Codex from technicalpickles/pickled-claude-plugins. It costs 0 tokens per session (3,059 once invoked), scanned A, original, MIT.

A guide to inspecting the internal code of command-line tools that wrap language models, such as Claude Code, Codex, or OpenCode.

In plain words
What is it for?
Use it to trace the code behind a displayed message, inspect prompts and tool descriptions, decode shortened names, or investigate undocumented settings.
Why use it?
It helps you find how the tool works when its documentation or source code does not explain a behaviour. It covers both readable source code and compiled program files.

Skill for Claude CodeCodex

Part of the agent-meta plugin — 4 skills shipped together

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 skills/technicalpickles/pickled-claude-plugins/harness-binary-spelunking
Any agent
npx skills add technicalpickles/pickled-claude-plugins --skill harness-binary-spelunking
Clone the repo
git clone --depth 1 https://github.com/technicalpickles/pickled-claude-plugins

Made for: Claude Code, Codex.

Or install agent-meta, the plugin that ships this one along with the rest of its 4 skills.

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 harness-binary-spelunking

README.md
[![agentmods](https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/harness-binary-spelunking.svg)](https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/harness-binary-spelunking)
Your own site
<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/harness-binary-spelunking"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/harness-binary-spelunking.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,059 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.03059
Opus 5 $0.00000 $0.01529
Sonnet 5 $0.00000 $0.00612
Haiku 4.5 $0.00000 $0.00306

Measured 4d ago against content hash 9e34929c00f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-binary-spelunking 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/extract-context.sh, scripts/spelunk-init.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/agent-meta/skills/harness-binary-spelunking/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Binary Spelunking

"The harness" here means whatever agent CLI you're inspecting: Claude Code, codex, opencode, pi, or any other tool that wraps an LLM in a terminal loop. The technique is the same regardless of which one you're looking at; only the recipes fork, based on how the binary was built.

Step 0: Decide your approach

Before grepping anything, figure out which situation you're in:

  • Open source, and the pinned version is tagged? Clone the source at that exact tag and read it. Fastest, most readable, no guessing at minified names. See references/source-clone.md.
  • Closed source (Claude Code today), or you want ground truth of what actually shipped? Spelunk the binary directly. Source, even when it exists, is what was committed; the binary is what's running on your machine right now.
  • Open source but the version isn't tagged yet, or you're debugging a discrepancy between source and behavior? Spelunk the binary even though source exists. "Open source" doesn't mean "skip verification."

Most investigations start at one of these two ends and only cross over if the first approach runs dry (source doesn't explain the behavior you're seeing; binary strings are too fragmented to be sure).

Identify the build and set up your workspace

If you're spelunking a binary (not reading source), run scripts/spelunk-init.sh before anything else. It resolves the binary, classifies the build, dumps strings once, and writes a manifest, all into a workspace shared by every recipe in this skill:

scripts/spelunk-init.sh claude
# Workspace ready: $TMPDIR/spelunk/claude
#   binary:      /path/to/the/real/binary
#   build type:  bun-js (bun markers: 7, rust markers: 118)
#   strings:     $TMPDIR/spelunk/claude/strings.txt
#   manifest:    $TMPDIR/spelunk/claude/manifest.txt

This exists because freelancing this step drifts fast: past investigations dumped to claude-strings.txt, then harness-strings.txt, with no per-tool suffix (so a second harness in the same session clobbers the first), and one reference file skipped the dump/reuse discipline entirely and re-ran strings on every recipe. One workspace shape, one script, no more re-deriving the path or the classification logic per investigation.

Read the full file on GitHub · 121 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 121 lines · 0 tokens per session scan A 9e34929c00f6

Subscribe to this mod's changes

harness-binary-spelunking is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (10 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,059 tokens. 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 skills, from other repositories