agent-patterns

agent-patterns is a skill for Claude Code from aAAaqwq/AGI-Super-Team. It costs 54 tokens per session (462 once invoked), scanned A, original, MIT.

A set of message formats and working rules for coordinating multiple coding agents. It defines how to assign tasks, report progress, describe problems, and combine results.

In plain words
What is it for?
Use it to write requests for parallel agents, produce status reports, handle failed or blocked work, and coordinate a multi-agent development sprint.
Why use it?
It gives agents a shared structure, so parallel work is easier to start, monitor, and merge without unclear handoffs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the agi-super-team plugin — 192 skills, 4 agents shipped together

Install

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.

agentmods
npx agentmods add skills/aaaaqwq/agi-super-team/agent-patterns
Any agent
npx skills add aAAaqwq/AGI-Super-Team --skill agent-patterns
Clone the repo
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team

Made for: Claude Code.

Or install agi-super-team, the plugin that ships this one along with the rest of its 192 skills, 4 agents.

Wrote 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.

agentmods badge for agent-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/agent-patterns.svg)](https://agentmods.dev/skills/aaaaqwq/agi-super-team/agent-patterns)
Your own site
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/agent-patterns"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/agent-patterns.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00462
Opus 5 $0.00027 $0.00231
Sonnet 5 $0.00011 $0.00092
Haiku 4.5 $0.00005 $0.00046

Measured 6d ago against content hash 1800313fbfac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-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 6d 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.

skills/agent-patterns/SKILL.md · 64 lines

What it actually says

Agent Patterns

Coordinate multi-agent workflows using structured communication protocols. Covers spawn requests, status reports, and inter-agent messaging within the sprint system.

Spawn Request Format

When launching a parallel agent, use this structure:

## SPAWN REQUEST
- **Agent ID**: <unique-id>
- **Role**: <role-name>
- **Task**: <one-line description>
- **Context**: <relevant files or state>
- **Expected Output**: <deliverable format>
- **Timeout**: <max duration>

Agent Report Format

Each agent reports back using:

## AGENT REPORT
- **Agent ID**: <id>
- **Status**: completed | failed | blocked
- **Summary**: <one-line result>
- **Output**: <deliverable or file path>
- **Issues**: <blockers or warnings, if any>
- **Duration**: <time taken>

Coordination Workflow

  1. Define tasks — break work into independent units suitable for parallel execution
  2. Spawn agents — send SPAWN REQUEST for each task with clear context
  3. Monitor status — track agent reports as they complete
  4. Handle failures — retry failed agents or reassign blocked tasks
  5. Merge results — combine agent outputs into final deliverable, resolving conflicts

Communication Rules

  • Agents communicate through structured reports, not free-form text
  • Each message includes agent ID for traceability
  • Blocked agents must report immediately rather than waiting silently
  • The coordinator agent reviews all reports before merging

Error Handling

See references/errors.md for common failure modes and recovery steps.

Examples

See references/examples.md for complete spawn-and-report workflows.

Files

What ships with it

3 files 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.

Changes

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.

  1. 6d ago First seen · 64 lines · 54 tokens per session scan A 1800313fbfac

Subscribe to this mod's changes

agent-patterns is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 462 once invoked, about $0.0003 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.