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.
git clone --depth 1 https://github.com/navraj007in/architecture-cowork-pluginWrote 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/navraj007in/architecture-cowork-plugin/blueprint-variants)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/blueprint-variants"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/blueprint-variants/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/blueprint-variants"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/blueprint-variants.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00019 | $0.04490 |
| Opus 5 | $0.00010 | $0.02245 |
| Sonnet 5 | $0.00004 | $0.00898 |
| Haiku 4.5 | $0.00002 | $0.00449 |
Grade A, and why
blueprint-variants scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:blueprint-variants
Generates 3-5 viable architecture options for a project based on constraints. Instead of a single "one-size-fits-all" blueprint, users see: baseline (recommended), cost-optimized, performance-optimized, and other variants with explicit trade-offs.
Trigger
/architect:blueprint-variants
/architect:blueprint-variants [--count 5] # show 5 options instead of 3
/architect:blueprint-variants [--baseline-only] # just show recommended, no variants
/architect:blueprint-variants [--constraints file.json] # load constraints from JSON
Purpose
Most teams have constraints (budget, team size, timeline, compliance needs). A single blueprint doesn't account for these. Blueprint-variants generates multiple architectures, each showing:
- Cost ($X/month)
- Complexity (1-10 scale)
- Team ramp time (weeks)
- Ops overhead (high/medium/low)
- Risk profile (low/medium/high)
- Key trade-offs vs. baseline
Users can compare, choose what fits their situation, and understand exactly what they gain/lose with each option.
Input
Context loading: Read architecture-output/_state.json first if it exists (project, tech_stack, components) — fall back to solution.sdl.yaml per the global SDL reading procedure only for details not already in _state.json.
If neither
_state.jsonnorsolution.sdl.yamlexists: "I need a project blueprint to generate variants from. Run/architect:blueprintfirst, then come back here."
Required: Project context from /architect:blueprint output (or provide interactively):
- Project type (web app, API, mobile backend, data pipeline, hybrid)
- Team expertise (startup, growing, mature)
- Primary concern (speed, cost, scale, compliance)
Optional: Constraint file (JSON):
{
"budget_monthly": 5000,
"team_size": 3,
"timeline_weeks": 8,
"ops_maturity": "startup",
"compliance_required": ["GDPR"],
"target_users": 10000
}
Output Files
1. architecture-output/options-comparison.md (always generated)
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.
- 12d ago First seen · 521 lines · 19 tokens per session scan A d512e2665d68
blueprint-variants is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 4,490 once invoked, about $0.0001 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
nyann:retrofit
Audit an existing repo against a profile and fix what's drifted. Unlike doctor (read-only), retrofit detects missing hooks, misconfigured gitignore, documentation gaps, and non-compliant history, then offers to remediate via bootstrap. Idempotent — safe to re-run.
nyann:apply
Apply an Infrastructure-as-Code change — the highest-stakes mutator in nyann; it can change real cloud infrastructure. Re-runs the plan, shows it, confirms, then applies. Unmistakably opt-in: apply is never the default and destructive applies require a second explicit confirm. For IaC apply intent only (not "apply a…
nyann:hotfix
Create the branch topology for a patch release against a previously tagged version. Ensures release/ . exists from the source tag, then creates hotfix/ off it. After this, the user commits the fix and runs /nyann:release from the hotfix branch.
nyann:release
Cut a release: generate a CHANGELOG section from Conventional Commits, make a release commit, and create an annotated tag. Defaults to conventional-changelog strategy.
nyann:ship
Open a GitHub pull request AND merge it in one step. Default uses GitHub's native auto-merge (returns immediately with outcome:"queued"); --client-side polls for green CI in the foreground then runs gh pr merge. Requires gh installed + authed.
nyann:cleanup-branches
Prune local branches whose work is already merged into the base. Lists candidates first, then applies on --yes. Mirrors the safe-delete semantics of git branch -d (lowercase d): nothing unmerged is touched.