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/next-steps)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/next-steps"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/next-steps/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/next-steps"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/next-steps.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 | $0.00024 | $0.02962 |
| Opus 5 | $0.00012 | $0.01481 |
| Sonnet 5 | $0.00005 | $0.00592 |
| Haiku 4.5 | $0.00002 | $0.00296 |
Grade A, and why
next-steps 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 11d 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:next-steps
Analyzes your project state (_state.json + _activity.jsonl) and recommends the 3 most impactful next commands to run. Saves ramp-up time, prevents wrong-sequencing, unblocks progress.
Trigger
/architect:next-steps
/architect:next-steps [--verbose] # show detailed reasoning
/architect:next-steps [--all] # show top 10 (not just 3)
Purpose
With 63 commands, users often ask: "What do I run next?"
This command answers it by:
- Detecting project stage (concept → mvp → growth → enterprise)
- Identifying what's done (from activity log history)
- Spotting blockers (missing prerequisites, stale outputs)
- Ranking by ROI (impact × urgency × dependency chain)
- Showing ETAs (estimated time to complete)
Example outputs:
Your project is at GROWTH stage. Next 3 commands:
1. 🔴 CRITICAL: /architect:generate-tests
→ Reason: Tests enable scaling confidence; currently missing for 8 components
→ Blocked by: Nothing (scaffold already done)
→ Est. time: 45 min
→ Why now: You've been implementing for 3 weeks without tests; technical debt risk high
2. 🟡 HIGH: /architect:design-system
→ Reason: Unify UI; colors/fonts inconsistent across team
→ Blocked by: Nothing (can run anytime)
→ Est. time: 15 min
→ Why now: Many new UI PRs; design tokens will reduce review friction
3. 🟢 MEDIUM: /architect:setup-monitoring
→ Reason: Observe production before launch; catch issues early
→ Blocked by: /architect:setup-cicd (deploy pipeline needed first)
→ Est. time: 20 min
→ Why now: You're 4 weeks from launch target; monitoring setup is critical path
Output
architecture-output/next-steps-guide.md (always generated)
# Next Steps Guide
**Generated:** 2026-04-24 14:32:10
**Project:** my-startup
**Current Stage:** growth
**Activity:** 47 commands run, 44 successful (94% success rate)
---
## Your Next 3 Priorities
### 1. 🔴 CRITICAL: /architect:generate-tests
**Reason:** Tests missing for 8 components; team velocity blocked by manual testing; tech debt risk high after 3 weeks of implementation
**What it does:**
- Generate unit, integration, e2e test suites
- 3 test frameworks supported (Jest, Vitest, Mocha)
- Auto-detect from scaffold structure
- Outputs ~500 test cases across components
**Prerequisites:** ✅ All met
- ✅ Scaffolded project exists
- ✅ SDL has entity definitions
- ✅ Source files exist (will be analyzed)
**Estimated time:** 45 minutes
**ROI:**
- Blocks: `/architect:production-readiness` (needs 80% test coverage)
- Enables: Confident refactoring, safer deployments
- Value: Reduce regressions 60-70%, catch bugs before production
**Next command after this:** `/architect:security-scan` (verify test patterns don't have holes)
**Run it:**
```bash
/architect:generate-tests
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.
- 11d ago First seen · 357 lines · 24 tokens per session scan A c4d22c466cc6
next-steps is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 2,962 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.