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/implement)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/implement"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/implement/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/implement"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/implement.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 | $0.00027 | $0.00555 |
| Opus 5 | $0.00014 | $0.00278 |
| Sonnet 5 | $0.00005 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
implement 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 9d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:implement
Trigger
/architect:implement <story-id | feature-description>
Arguments
| Format | Example | Resolution |
|---|---|---|
| Story ID | S1.3, Story 2.4, US-42 |
Looked up in architecture-output/sprint-backlog.md |
| Scoped feature | api-server:password-reset |
Component name + feature slug |
| Free-text | "add email notification on order placed" |
Normalized to feature slug |
Purpose
Implements one feature end-to-end into a codebase that was bootstrapped by /architect:scaffold or /architect:scaffold-component. Reads the codebase first to match its exact patterns. Never overwrites working code. Never refactors architecture. One story per invocation.
This is the iterative development command — it operates on existing code, not fresh directories.
Out of Scope
This command will NOT:
- Rename, move, or restructure existing files
- Change existing function signatures
- Refactor logic unrelated to the feature being implemented
- Run database migrations (produces the migration file, documents the manual step)
- Bootstrap a new component from scratch — use
/architect:scaffold-component - Implement multiple stories in one invocation
- Touch files not in the write plan
Conflict protocol: If implementing the feature requires changing an existing signature or refactoring shared logic, stop, explain the conflict, and tell the developer what to resolve manually before re-invoking.
Workflow
This command is split across two files for size:
- Steps 1–4 (story resolution, context, pattern detection, write plan):
command-parts/implement-1.md - Steps 5–10 (file writing, wiring, build verification, summary, activity log, signal completion):
command-parts/implement-2.md
Read command-parts/implement-1.md first, then command-parts/implement-2.md (paths relative to the plugin root). For components with more than one runtime, delegate each component to the implementer agent (agents/implementer.md) so build failures in one component do not block another.
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.
- 9d ago First seen · 50 lines · 27 tokens per session scan A a5ec7aec7f9a
implement is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 555 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:doctor
Run nyann's read-only hygiene + documentation audit on the current repo. Emits the same drift sections retrofit uses, but never offers remediation or writes to the filesystem. Use this on session start, in CI, or any time you want to sanity-check a repo without risking mutations.
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: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: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: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.
nyann:gh-protect
Audit or apply GitHub branch protection, tag rulesets, signing requirements, and repo settings based on the active profile.