truestack-reverse-engineering

truestack-reverse-engineering is a skill for Claude Code from adtn0810/truestack. It costs 185 tokens per session (1,606 once invoked), scanned A, original, MIT.

A method for studying a concrete reference, such as a code repository, code sample, document, specification, or older system, to build a checked understanding of how it works. It then uses that understanding to plan a safe change to your own system.

In plain words
What is it for?
Use it when you provide an artifact and want to understand its design, behavior, or upgrade path. It can examine authorized code or systems, consider provenance and licensing, and turn the findings into an adaptation plan.
Why use it?
It avoids copying or modifying something based on guesses about its behavior. It separates facts confirmed from the reference from conclusions that are only inferred.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the truestack plugin — 23 skills, 8 commands, 2 hooks shipped together

Good fit Use it when you provide an artifact and want to understand its design, behavior, or upgrade path. It can examine authorized code or systems, consider provenance and licensing, and turn the findings into an adaptation plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adtn0810/truestack/truestack-reverse-engineering
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.

Any agent
npx skills add adtn0810/truestack --skill truestack-reverse-engineering
Clone the repo
git clone --depth 1 https://github.com/adtn0810/truestack

Made for: Claude Code.

Or install truestack, the plugin that ships this one along with the rest of its 23 skills, 8 commands, 2 hooks.

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 truestack-reverse-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-reverse-engineering/github.svg)](https://agentmods.dev/skills/adtn0810/truestack/truestack-reverse-engineering)
Your own site
<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-reverse-engineering"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-reverse-engineering/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 truestack-reverse-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-reverse-engineering"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-reverse-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,606 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00185 $0.01606
Opus 5 $0.00093 $0.00803
Sonnet 5 $0.00037 $0.00321
Haiku 4.5 $0.00018 $0.00161

Measured 9d ago against content hash 4e2bb68c73e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

truestack-reverse-engineering 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.

skills/truestack-reverse-engineering/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

truestack-reverse-engineering

Not this skill: a "how does X achieve this" question with no artifact to opentruestack-deep-research; routine onboarding of your own repo → truestack-project-memory.

Understand the reference for real, then adapt — not clone. The deliverable is a verified model of how it works and why, turned into a safe upgrade for the user's system. Honesty over assumption: a guess about how code works is a future bug, so every claim is grounded in the actual artifact and labelled verified vs inferred. Adapt the idea; respect the IP.

Read project memory first — CLAUDE.md is auto-loaded (Principles + Boundaries); consult .ai/memory/ for the user's stack and conventions so the upgrade grafts onto what's really there. If none exists, run truestack-project-memory. Authorized targets only: the reference must be something the user may study — their own code, OSS under a compatible license, or a system they're cleared to analyze. Studying a system's observable behaviour to rebuild a capability is legitimate; exfiltrating secrets or defeating protection for misuse is not — decline that and say why.

1. Scope, provenance, and license — before reading deeply

Establish what the reference is (repo / snippet / binary / doc), where it came from, and under what license. Record the license and any constraint (copyleft, attribution, no-derivatives). Then frame the real question: "how does it do X" (learn) vs "get its capability into my system" (adopt). If the goal is to adopt code (not just the idea), license compatibility is an Ask-first gate — never paste licensed/proprietary source into the user's tree without an explicit yes.

2. Map the spine before the details (static pass)

Read outside-in: entry points, the module/dependency graph, the data model, the key interfaces, and configuration. Name the architecture style and the few load-bearing decisions that make it work. Don't drown in line-by-line reading — find the spine first. Track what you can read directly (verified) separately from what you can only infer.

Read the full file on GitHub · 92 lines

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 · 92 lines · 185 tokens per session scan A 4e2bb68c73e6

Subscribe to this mod's changes

truestack-reverse-engineering is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 185 tokens to every session and 1,606 once invoked, about $0.0009 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.