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/rajconnects/founder-stack/architecture-reviewgit clone --depth 1 https://github.com/rajconnects/founder-stackWrote 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/rajconnects/founder-stack/architecture-review)<a href="https://agentmods.dev/commands/rajconnects/founder-stack/architecture-review"><img src="https://agentmods.dev/badge/commands/rajconnects/founder-stack/architecture-review.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 | $0.00051 | $0.01241 |
| Opus 5 | $0.00026 | $0.00620 |
| Sonnet 5 | $0.00010 | $0.00248 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
architecture-review 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 4d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running an architecture review. The aim is to surface refactoring opportunities that turn shallow modules into deep ones — improving testability, AI-navigability, and locality of change.
Arguments: $ARGUMENTS
Vocabulary (use these terms exactly)
- Module — anything with an interface and an implementation.
- Interface — everything a caller must know: types, invariants, error modes, ordering, config. Not just signature.
- Depth — leverage at the interface. Deep = a lot of behaviour behind a small interface. Shallow = interface nearly as complex as the implementation.
- Seam — where an interface lives; a place behaviour can be altered without editing in place.
- Locality — change, bug, and knowledge concentrated in one place.
- Deletion test — imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it earned its keep.
Steps
-
Resolve scope.
- If
$ARGUMENTSis a phase identifier (e.g.7a), use the corresponding handoff doc and recent commits to define scope. - If
$ARGUMENTSis a path, scope to that subtree. - If
$ARGUMENTSis empty, ask: "Review which scope? A phase identifier (e.g.7a) or a path."
- If
-
Read project conventions. Read
.claude/project.json. Extract:context_doc,glossary_doc,glossary_anchor— vocabulary discipline.decision_records.pathanddecision_records.format— to avoid re-litigating settled decisions.architecture_notes— long-form memos to respect.handoff_output_dir— for phase handoff lookup.test_roots— to weigh test surface in the deepening analysis.
-
Read the project's thinking.
- Glossary section.
- Decision records relevant to the scope (filter by topic mention, status
resolved). - Any architecture note whose filename mentions the scope.
- The handoff doc for the scoped phase, if applicable.
-
Explore the scope. Use the
Exploresubagent or direct Read/Grep/Glob. Look for:- Modules whose interface is nearly as complex as their implementation (shallow).
- Pure functions extracted only for testability where the real bugs hide in how they're called (no locality).
- Tightly-coupled clusters that leak across seams.
- Untested code paths or paths that are hard to test through their current interface.
- Where understanding one concept requires bouncing across many small modules.
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.
- 4d ago First seen · 85 lines · 51 tokens per session scan A 0c2e89f48a71
architecture-review is a command published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,241 once invoked, about $0.0003 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.