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/ai-driven-dev/framework/01-generate-agentgit clone --depth 1 https://github.com/ai-driven-dev/frameworkWhat 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 | $0.00014 | $0.00368 |
| Opus 5 | $0.00007 | $0.00184 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
generate_agent 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 yesterday.
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.
What it actually says
Goal
Generate a specialized agent template tailored to specific user requirements.
Context
Coordination with other agents
@../../references/agents-coordination.md
Agent template
@../../assets/agents/agent-template.md
AI Mapping
Apply tool-native conventions for agent file paths, naming, and extensions.
@../../references/ai-mapping.md
Rules
- Input and Output for the agent MUST be ULTRA concise and precise.
- Ask clarifying questions if the user's request is ambiguous or lacks detail.
- When mentioning templates in
aidd_docs, always provide full path
Instruction steps
- Ask following questions to the user until you gather all necessary information in agent's template.
- Discuss with the user until you have a clear understanding of the agent's purpose, tools, and instructions.
- Use the gathered information to fill in the agent template.
- Review the generated agent to ensure it is straightforward with 0 ambiguity.
- Affect a note between 1 and 10 to the generated agent based on its relevance and completeness.
- Wait for user confirmation before finalizing the agent.
- Propose 3 real first names for the agent, each name must be short and catchy, making sense with the agent's purpose (could be word game, acronym, etc.).
- Provide the completed agent template as the final output, written to the AI tool's native agents directory as
<generated-agent-name>.md. - Add the new prompt into the
@aidd_docs/CATALOG.mdto keep documentation up to date.
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.
- yesterday First seen · 50 lines · 14 tokens per session scan A df5c28f78dc9
generate_agent is an agent published in the GitHub repository ai-driven-dev/framework (445 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 368 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
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
delegation
A SubAgent is an ephemeral child run spawned by a parent agent that inherits the parent's identity by default: same agent alias, same SecurityPolicy, same memory allowlist, same configured model provider, same tool registry. Auditable as a child via a tracing span agent. .subagent. .
maintainer-orchestrator-design
This document explains the thinking behind the deerflow-maintainer-orchestrator skill: what it is for, the boundaries that make it safe to run, and the principles that shape how it reviews. It is written for DeerFlow maintainers who run the skill, and for anyone in the community who wants to understand — or adapt …
history-management
The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.
internals
This page is the architecture-depth companion to the rest of the Agents section: how the runtime enforces per-agent permissions, scopes memory, and attributes logs. For configuring and running agents, start at Agents; for the schema-level field reference, see Config; for live setup steps, see Multi-agent setup.