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-agent-coordinationgit 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-agent-coordination)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-agent-coordination"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-agent-coordination/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-agent-coordination"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-agent-coordination.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 | $0.00094 | $0.01097 |
| Opus 5 | $0.00047 | $0.00549 |
| Sonnet 5 | $0.00019 | $0.00219 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
truestack-agent-coordination 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-agent-coordination
Multiple agents go fast only when ownership is clean and the merge path is engineered — the classic failure is uncoordinated parallel writes cascading across everyone. Keep two mechanisms separate: isolation stops agents overwriting each other's files; coordination stops them disagreeing on contracts and tasks. You need both.
Go parallel only when it pays
Right-size first. Small, sequential, or tightly dependent work stays single-agent — coordination overhead grows faster than linearly with agent count, and review (not the model) is the real bottleneck. Parallelize only genuinely independent work. Start with 2–3 agents; ~5–10 is the practical ceiling before merging dominates.
1. Plan and decompose before spawning anything
As the orchestrator, and with human approval before dispatch:
- Define shared contracts first — API request/response shapes, TypeScript interfaces, the DB schema/migration. Never let parallel agents invent these independently.
- One non-overlapping scope per task — a directory, a layer, a test surface; not an abstract idea. Overlapping paths cause merge conflicts even with isolation.
- SPEC-test each task before dispatch: clear scope, single owner, explicit acceptance criteria, a done/test command. If you can't specify it cleanly, you lack context — gather more, don't dispatch.
- Map dependencies: serialize dependent tasks into phases, parallelize independent ones (Phase 1: schema + scaffolding in parallel → Phase 2: routes → Phase 3: tests + docs).
- Off-limits unless assigned: lockfiles, migrations, root config, shared interfaces.
2. Isolate every writing agent
Give each implementing agent its own git worktree + branch so parallel sessions never
touch the same working files (Claude Code: launch the subagent with isolation: worktree,
or run separate sessions in git worktree add checkouts). Per-worktree CLAUDE.md, plan, and
memory come along automatically. Read-only research/explore agents don't need isolation —
unless they run scripts, install packages, or otherwise perturb the directory.
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 · 74 lines · 94 tokens per session scan A 55c13d3b3fc4
truestack-agent-coordination is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 1,097 once invoked, about $0.0005 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.
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…
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.