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-architecture-planninggit 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-architecture-planning)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-architecture-planning"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-architecture-planning/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-architecture-planning"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-architecture-planning.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 | $0.00165 | $0.01781 |
| Opus 5 | $0.00082 | $0.00890 |
| Sonnet 5 | $0.00033 | $0.00356 |
| Haiku 4.5 | $0.00016 | $0.00178 |
Grade A, and why
truestack-architecture-planning 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 12d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-architecture-planning
The prompt is evidence of intent, not a finished spec. Plan first, code never (here):
this skill produces an architecture the user signs off on before truestack-backend-development runs. Aim
for the simplest design that meets the real requirements — on a self-hosted single
server, every extra layer is a permanent tax, so justify each one.
First, read project memory — CLAUDE.md is auto-loaded (including its Principles and
Boundaries); consult .ai/memory/ for deeper detail. If no memory exists yet, run
truestack-project-memory before planning anything substantial.
Right-size the work (do this first)
Match the ceremony to the size of the change — heavy process on a small task is its own
failure mode. (These are the same tiers truestack-orchestrate right-sizes with — if the
two texts ever disagree, orchestrate's definitions are canonical.)
- Trivial (rename, copy tweak, one-liner) and unambiguous: skip planning; go straight to
truestack-backend-development+truestack-quality-control. If even a small ask is ambiguous, clarify first (see step 6). - Small (contained, clear intent): a short plan — goal, approach, testable criteria. Skip interpretations and task breakdown.
- Substantial (new feature/service, several moving parts): the full flow below.
- High-risk (irreversible / data / security / money): the full flow plus the approval gate.
1. Frame the real work
If the request rests on a false premise or won't actually achieve the user's goal, say so plainly before planning — don't design around a misunderstanding to be agreeable.
- Restate the goal in one or two sentences. If the request is vague, don't pretend it's precise.
- Separate outcome from requested solution: what the user actually wants vs. the approach they named, and what would make that approach wrong or insufficient.
- List interpretations when more than one reading exists (minimal / expanded / alternative). Skip for trivial/small work.
- Name the decisions that change the design: users, data in/out, business rules, scale, permissions, error/edge behavior, integrations, persistence, ops.
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.
- 12d ago First seen · 121 lines · 165 tokens per session scan A b44b515b9af2
truestack-architecture-planning is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 165 tokens to every session and 1,781 once invoked, about $0.0008 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
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
build-ui-components-and-systems
A guide for building reusable UI components and design systems: shared visual rules, component interfaces, behavior, accessibility requirements, documentation, packaging, and version management. A design system is a maintained set of parts and rules that multiple screens or products can share.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…