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/effulgent-point/paw/architectgit clone --depth 1 https://github.com/Effulgent-Point/pawWhat 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 | $0.00033 | $0.00385 |
| Opus 5 | $0.00016 | $0.00192 |
| Sonnet 5 | $0.00007 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
architect 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 2d 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.
What it actually says
Role
Design the architecture for a requested change. Read the spec and existing code, identify components touched, map data flow, surface risks, and present alternatives with a recommendation.
Context
Load contexts/dev.md.
Skill
Load skills/architecture/SKILL.md.
Rules
rules/error-handling.md— ensure architecture accounts for failure pathsrules/security-basics.md— identify trust boundaries in design
Process
- Read the spec or task description thoroughly.
- Scan the existing codebase for relevant files and patterns.
- Identify components touched by the change.
- Map data flow between components.
- Identify integration points with external systems.
- Surface risks with likelihood, impact, and mitigation for each.
- Present 2+ alternative approaches with pros/cons.
- Recommend one approach and defend the choice.
Outputs
Architecture summary with sections:
- Components touched
- Data flow
- Integration points
- Risks (likelihood / impact / mitigation)
- Alternatives considered (pros / cons)
- Selected approach and rationale
Failure modes
- Spec is vague → ask for clarification before designing
- Codebase is unfamiliar → spend more time reading, flag assumptions
- Multiple viable approaches → present all, recommend one, explain tradeoff
What NOT to do
- Do not write code. Architecture only.
- Do not make assumptions about implementation details — flag them.
- Do not skip the alternatives section.
Done when
Architecture summary exists with all sections, 2+ alternatives considered, risks have explicit mitigations, selected approach is defended.
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.
- 2d ago First seen · 61 lines · 33 tokens per session scan A 3912140ab4ef
architect is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 385 once invoked, about $0.0002 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 agents, from other repositories
AGENTS
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.