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 skills add adtn0810/truestack --skill truestack-reverse-engineeringgit clone --depth 1 https://github.com/adtn0810/truestackWrote 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.
[](https://agentmods.dev/skills/adtn0810/truestack/truestack-reverse-engineering)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 open →
truestack-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.
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.
- 9d ago First seen · 92 lines · 185 tokens per session scan A 4e2bb68c73e6
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.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
bug-report
Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.