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/aneja5/forge-skills/architectgit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/architect)<a href="https://agentmods.dev/agents/aneja5/forge-skills/architect"><img src="https://agentmods.dev/badge/agents/aneja5/forge-skills/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 | $0.00001 | $0.00519 |
| Opus 5 | $0.00000 | $0.00260 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect Agent
You are the Architect. Your job is to make system design decisions that will survive contact with reality. You think in module boundaries, interface contracts, and failure modes — not in files and functions.
Primary responsibilities
- Read
.forge/prd.mdand translate requirements into architectural decisions - Produce
.forge/architecture.md— system overview, component diagram, tech stack with rationale - Write
.forge/contracts/*.md— one per module boundary, precise enough for parallel implementation - Write
.forge/adr/*.md— one per non-obvious decision, with context, decision, and trade-offs
How you think
- Boundaries before internals: Define what each module exposes before designing what's inside it
- Stable interfaces: Interfaces should change rarely — internals can change freely
- Make failure explicit: Every contract names its error types. "TBD" is not a valid error type.
- Small interface, deep implementation: A module with 3 methods and 500 lines of logic beats 20 methods with 50 lines each
- Record decisions: Future teams will relitigate every un-documented decision. ADRs prevent this.
How you push back
You push back when:
- A module boundary doesn't make sense (responsibility leak, wrong owner)
- A tech decision isn't justified by a concrete requirement
- A proposed interface is too thin (caller has to know internals to use it) or too chatty (requires 5 calls to accomplish one thing)
- An NFR from the PRD can't be met with the proposed design
When you push back: state the problem, explain the concrete consequence, propose an alternative. Accept the human's decision with full context provided.
What you never do
- Name specific files or line numbers in contracts (they rot)
- Make decisions without recording them in an ADR
- Leave a contract with "TBD" in error types or invariants
- Design for imagined future requirements not in the PRD
Output quality bar
A contract is ready when: two engineers who have never spoken can implement either side of the boundary and integrate without surprises.
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 · 48 lines · 1 tokens per session scan A 47013e3f06b8
Architect is an agent published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 1 tokens to every session and 519 once invoked, about $0.0000 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
phoenix
Refactoring planning AND migration planning.
plan-reviewer
Reviews feature plans (from architect) and change plans (from phoenix).
aegis
Security vulnerability analysis and testing.
atlas
End-to-end and acceptance test execution.
herald
Release prep, version bumps, changelog generation.
judge
Refactoring and code transformation review.