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 agentmods add agents/microsoft/multi-agent-custom-automation-engine-solution-accelerator/speckit.contentpackgit clone --depth 1 https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-AcceleratorWrote 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/agents/microsoft/multi-agent-custom-automation-engine-solution-accelerator/speckit.contentpack)<a href="https://agentmods.dev/agents/microsoft/multi-agent-custom-automation-engine-solution-accelerator/speckit.contentpack"><img src="https://agentmods.dev/badge/agents/microsoft/multi-agent-custom-automation-engine-solution-accelerator/speckit.contentpack.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.02456 |
| Opus 5 | $0.00012 | $0.01228 |
| Sonnet 5 | $0.00005 | $0.00491 |
| Haiku 4.5 | $0.00002 | $0.00246 |
Grade A, and why
speckit.contentpack 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 4d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Packs
Optional, drop-in extensions to the Multi-Agent Custom Automation Engine. A pack ships everything needed to add a domain-specific agent team without touching core code.
The core solution works fine when the content_packs/ folder is empty or absent.
Folder Structure
content_packs/
└── <pack_name>/
├── pack.json # optional — declares search indexes + blob uploads
├── agent_teams/
│ └── *.json # required — one or more team config files (any name)
├── datasets/ # optional — source data for grounding
│ ├── data/*.csv
│ └── docs/*.pdf
└── scripts/ # optional — pack-local utilities
<pack_name>should be lowercase snake_case (e.g.pet_food,legal_review).- JSON files inside
agent_teams/can be named anything — the upload script globs all*.jsonfiles in that directory.
Designing Your Agent Team
Every pack needs at least one team config JSON in agent_teams/. The agents you
create should be tailored to your domain — there is no fixed pattern. Consider:
What does the user need? Design agents around the tasks your users will perform, not around a template. Ask yourself:
| Question | Design decision |
|---|---|
| Does the team need to look up data? | Add a ResearchAgent with use_knowledge_base: true |
| Does it need to generate images? | Add an agent with use_toolbox: true and the appropriate toolbox_filter |
| Should it ask the user clarifying questions? | Set user_responses: true on the relevant agent |
| Are there multiple distinct tasks? | Add specialist agents and a TriageAgent to route between them |
| Is it a simple Q&A over data? | A single agent with KB access may be enough — no triage needed |
Examples from this repo:
| Pack | Agents | Why |
|---|---|---|
content_gen |
Triage → Planning → Research → TextContent → ImageContent → Compliance | Complex creative workflow with multiple output types |
contract_compliance |
Triage → Research → Analysis | Document review with KB lookup |
hr_onboarding |
Single team (no KB) | Workflow-only, no data grounding needed |
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.
- 4d ago First seen · 274 lines · 24 tokens per session scan A 9cb10c9eac03
speckit.contentpack is an agent published in the GitHub repository microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator (878 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 2,456 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
triager
Triage old stale issues for obsolescence and recommend closures.
fixer
Fix and verify issues in app.
architecture
Analyzes GPT-RAG boundaries, contracts, security, deployment topology, and trade-offs. Use for structural or hard-to-reverse changes; do not use for local implementation work with settled requirements.
implementation
Implements, tests, and documents scoped GPT-RAG changes after requirements are clear. Do not use to decide broad architecture or publish releases.
release
Prepares and validates GPT-RAG multi-repository releases. Use for manifest pins, changelog entries, release branches, and release notes; do not use for feature implementation or publish without explicit human approval.
Codebase-Explorer
Help engineers learn about the codebase and programming concepts of this project.