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-orchestrategit 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-orchestrate)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-orchestrate"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-orchestrate/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-orchestrate"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-orchestrate.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 | $0.00131 | $0.02543 |
| Opus 5 | $0.00066 | $0.01272 |
| Sonnet 5 | $0.00026 | $0.00509 |
| Haiku 4.5 | $0.00013 | $0.00254 |
Grade A, and why
truestack-orchestrate 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-orchestrate
One coding request often needs planning, building, an external call, and a quality gate — in a specific order, with the right contracts applied at each step. This skill is the router: it doesn't do the work itself, it routes to the skill that does and makes sure the chain runs in sequence. Front door of the set — classify the request, dispatch, check the handoff, repeat.
Don't duplicate a skill's content here. Orchestrate decides which skill and in what order; each skill owns its own method — the sibling's own description is the source of truth for what it covers.
Step 0 — ground before routing (always)
- Read project memory —
CLAUDE.mdis auto-loaded (Principles + Boundaries); read.ai/memory/on demand. If no memory exists, route to truestack-project-memory to build it before any substantial work. - Carry the always-on contracts into whatever runs next: honesty (ground / verify / abstain, truth over agreement), auto-research (consequential current-fact decisions are grounded in authoritative sources before committing, not recalled), clarify-then-proceed on real ambiguity, and the Ask-first / Never boundaries. They travel with every route; the destination skill enforces it.
- Right-size (below) so heavy process never lands on a one-liner.
Right-size first
- Trivial & unambiguous (rename, copy tweak, one-liner): skip orchestration — the one obvious skill, then truestack-quality-control.
- Small (contained, clear intent): the single relevant skill → truestack-quality-control.
- Substantial (feature / service, several moving parts): run the full chain.
- High-risk (irreversible · data · money · security · schema / migration · first prod deploy · auth/credential or privacy-policy design): full chain plus the truestack-architecture-planning approval gate before any code is written; route risky DDL/backfill through truestack-database-migrations (if the
hooks/PreToolUse gate is wired in this install it also trips there — confirm it's active rather than assuming; if unwired, the approval gate is the only barrier).
What ships with it
1 file 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.
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 · 122 lines · 131 tokens per session scan A 75f3b4313185
truestack-orchestrate is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 131 tokens to every session and 2,543 once invoked, about $0.0007 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…