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 skills/archastro/archagents/archagent-integration-patternsnpx skills add ArchAstro/archagents --skill archagent-integration-patternsgit clone --depth 1 https://github.com/ArchAstro/archagentsWhat 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 | $0.00082 | $0.01325 |
| Opus 5 | $0.00041 | $0.00662 |
| Sonnet 5 | $0.00016 | $0.00265 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
archagent-integration-patterns 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 3d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Patterns
Most customer integrations collapse to one of seven shapes. When a
customer describes what they want, map it to the closest pattern below
and produce the minimal agent.yaml snippet. Then load the deeper
skill (archagent-author-agent, archagent-build-script, archagent-build-workflow) to fill in
details.
Pattern 1 — GitHub PR review
Use when: customer wants to review PRs, triage issues, or react to pushes.
installations:
- kind: integration/github
config: {}
routines:
- name: review-prs
handler_type: preset
preset_name: do_task
event_type: webhook.github_app.pull_request
event_config:
webhook.github_app.pull_request:
filters: {}
status: active
Critical: GitHub sends multiple events per PR. Enforce
action in {"opened", "synchronize"} filter or in the identity
prompt, otherwise the agent reviews the same PR N times.
Reference sample: agents/code-review-agent in this repo.
Pattern 2 — Slack bot
Use when: the customer's users should talk to the agent in Slack.
Install the Slack app installation. The simplest shape uses
thread.session.join + the participate preset — Slack messages get
proxied into threads automatically.
installations:
- kind: archastro/thread
config: {}
- kind: integration/slack
config: {}
routines:
- name: participate-slack
handler_type: preset
preset_name: participate
event_type: thread.session.join
event_config:
thread.session.join:
filters: {}
To post outbound (from scripts/workflows), use the slack script
namespace: let slack = import("slack"); unwrap(slack.post_message(...)).
Pattern 3 — Scheduled job
Use when: "run every Monday at 9am", "check this feed every hour".
routines:
- name: weekly-digest
handler_type: preset
preset_name: do_task
event_type: schedule.cron
schedule: "0 9 * * 1"
event_config:
schedule.cron:
filters: {}
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.
- 3d ago First seen · 188 lines · 82 tokens per session scan A 6b3de4c9908b
archagent-integration-patterns is a skill published in the GitHub repository ArchAstro/archagents (5 stars, last pushed 17d ago), licensed MIT. It adds 82 tokens to every session and 1,325 once invoked, about $0.0004 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
test-review
You are an expert DataHub test reviewer. Your role is to evaluate smoke tests and integration tests against established testing standards, identify issues, and provide actionable feedback.
create-agent
Help users create and configure openma managed agents through conversation. Trigger when users say "create an agent", "I need an agent that...", "set up an agent for", "build me a bot", or describe a task to automate. Also trigger for "Create with AI" from Dashboard. Also use when users ask about the openma platform…
openma
Use the openma platform to build, deploy, and manage AI agents. Trigger when users want to create agents, start sessions, manage environments, configure model cards, handle vaults/credentials, install skills, connect MCP servers, or interact with the openma HTTP API. Also trigger when users mention "oma", "openma"…
openhermit-admin
Explain what OpenHermit is and how to deploy and administer it — setup, CLI, gateway, agent config, API. Use when the user asks about installing, operating, or administering an OpenHermit deployment. For how agents behave for their owners/users/guests, see openhermit-guide.
skill-creator
Create, structure, and validate new skills. Use when designing a skill, scaffolding a skill directory, or improving an existing skill.
docx
Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.