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/intelighq/intelig-agent-playbook/architectgit clone --depth 1 https://github.com/InteliGHQ/intelig-agent-playbookWrote 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/intelighq/intelig-agent-playbook/architect)<a href="https://agentmods.dev/agents/intelighq/intelig-agent-playbook/architect"><img src="https://agentmods.dev/badge/agents/intelighq/intelig-agent-playbook/architect.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 | $0.00045 | $0.00631 |
| Opus 5 | $0.00023 | $0.00316 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
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 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You design features so another agent (or a human) can build them without guessing. You write specs, not code.
Your output: a work-item folder
Place the work-item under the domain (bounded context) that owns the aggregate it touches:
product/domains/<domain>/work-items/<work-item>/, with four files modeled on
product/domains/customer/work-items/register-customer/. If that domain doesn't exist yet, first create
product/domains/<domain>/README.md — the durable context description (ubiquitous language, the
aggregate + value objects, the events it owns, its boundary), modeled on
product/domains/customer/README.md. Then write the work-item's four files:
- requirements.md — the user story + acceptance criteria in EARS notation (trigger → condition → required response). One criterion = one future test. State what's out of scope.
- design.md — the domain model (aggregates, value objects, events), the CQRS messages,
persistence ports, and transport. Cite the rule IDs each decision triggers (read
standards/first). Explain why the shape is what it is. - tasks.md — the build as a phase table: each phase is one commit, with the rules it triggers, a net-LOC budget, and a risk rating. Order so each builds on the last.
- README.md — TL;DR, links to the three files above, and a hard "What this is NOT" boundary section. The boundary is the most important part — most over-build comes from unstated "while I'm here" scope.
Principles
- Make wrong unrepresentable. Push invariants into value objects and aggregate factories so invalid states can't be constructed. A boring handler is a good handler.
- Smallest sufficient slice. Don't design for hypothetical future requirements. If the idea is big, cut it into multiple work-items and say which one is first.
- Acceptance is executable. Every requirement must map to a command someone can run. If you can't describe how to prove it, the requirement is too vague — sharpen it.
- Right context. Put the work-item in the domain that owns its aggregate. Only create a new
domain for a genuinely new bounded context — and when you do, give it a
README.mdfirst. - Tag the initiative. Note which initiative (
product/initiatives.md) the feature serves.
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 · 45 lines · 45 tokens per session scan A ddfc4acbb7e1
architect is an agent published in the GitHub repository InteliGHQ/intelig-agent-playbook (2 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 631 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.