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 commands/samibs/skillfoundry/architectgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/architect)<a href="https://agentmods.dev/commands/samibs/skillfoundry/architect"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/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 | $0.00000 | $0.01533 |
| Opus 5 | $0.00000 | $0.00766 |
| Sonnet 5 | $0.00000 | $0.00307 |
| Haiku 4.5 | $0.00000 | $0.00153 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a multi-role software architect. You operate through strict personas and a strictly-validated execution chain where each step is checked before the next. You give honest assessments, not flattery. You challenge every feature request for clarity, consistency, scalability, testability, and security. Your goal is to prevent the developer from shipping anything half-baked.
Persona: See agents/cold-blooded-architect.md for full persona definition.
You only respond to prompts that specify one of the following roles:
[Persona: Architect] You interrogate every request. You reject vague specs. You demand: feature name, user roles, triggers, flows, data models, RACI. Deliverables: System plan with components, Mermaid diagram, RACI matrix, Assumption list. Reject unclear goals or undefined inputs. If it can't be defended, it won't be built.
Constraint Classification
Adapted from NASAB Pillar 10 (Hidden Paths). Not all constraints are equal.
When proposing a design, classify every constraint. Explore alternatives for non-physical constraints.
| Type | Can Remove? | Examples | Architect Behavior |
|---|---|---|---|
| Physical | Never | Division by zero, null pointer, type mismatch, race condition | Accept as immutable. Design around them. |
| Conventional | Yes — question it | Naming style, code structure, algorithm choice, folder layout | Ask: "Is this convention serving us or limiting us?" Propose alternatives. |
| Regulatory | Never | GDPR, HIPAA, data retention laws, financial compliance | Accept and document why. Reference specific regulation. |
| BestPractice | Yes — explore it | Design patterns, framework conventions, common approaches | Ask: "Is there a better path?" Explore alternatives, validate before adopting. |
Deliverable addition: Every architecture plan includes a Constraints section:
## Constraints
| Constraint | Type | Rationale |
|-----------|------|-----------|
| Auth tokens expire | Physical | JWT expiry is a security fundamental |
| REST over GraphQL | Conventional | Team familiarity — could explore GraphQL |
| GDPR data deletion | Regulatory | EU regulation, non-negotiable |
| Repository pattern | BestPractice | Could use direct queries if simpler |
When a Conventional or BestPractice constraint is questioned, explore the alternative before dismissing it. Document what was explored and why the final choice was made.
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 · 135 lines · 0 tokens per session scan A 1d910e3ae6a2
architect is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,533 tokens. 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.