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/production-readiness)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/production-readiness"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/production-readiness/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/production-readiness"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/production-readiness.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 | $0.05159 |
| Opus 5 | $0.00010 | $0.02580 |
| Sonnet 5 | $0.00004 | $0.01032 |
| Haiku 4.5 | $0.00002 | $0.00516 |
Grade A, and why
production-readiness scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Grep source files for outbound HTTP call patterns: `axios.get`, `fetch(`, `httpx.get`, `http.Get` How it starts
The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:production-readiness
Trigger
/architect:production-readiness
/architect:production-readiness --component <name> # scope to a single component
Purpose
Analyses actual source code across all components to determine whether the project is safe to launch. Reads route files, middleware, schema, migrations, environment config, test files, and SDL to score 8 categories. Produces a prioritised gap list (P0 blockers / P1 required / P2 recommended) and a single go/no-go verdict.
Distinct from /architect:launch-check — that command is a 30-second file-presence scan suitable for CI gates. This command reads and analyses source code content. Run it as the final sign-off before going to production.
Does not re-run other commands. If security-scan.md, _state.json.test_suite, or monitoring config already exist, this command reads their outputs rather than repeating the analysis.
Workflow
Step 1: Load project context
Follow the Context Loading Pattern:
-
Read
architecture-output/_state.jsonin full. Extract:project.name,project.type,project.stagetech_stack— framework, ORM, auth provider, integrationscomponents[]— names, types, portstest_suite— coverage target, frameworks (ifgenerate-testswas run)monitoring— providers configured (ifsetup-monitoringwas run)compliance— frameworks, critical gaps (ifcompliancewas run)
-
Read
solution.sdl.yaml(orsdl/module files). Grep for:slos:→slos.services[].availability— used to enforce observability thresholdcompliance:→ frameworks in scopetesting:→ e2eFramework, coverageTargetcontracts:→contracts.apis[]— used to verify API contract shapefeatures:→ features with statusdone— used to verify critical paths are tested
-
If
--component <name>was passed, scope all subsequent steps to that component's directory only. -
Collect the component directory list:
- From
_state.json.components[]— usenamefield to find directories - Fall back to Glob for directories containing
package.json,pyproject.toml,go.mod, or*.csproj
- From
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 · 452 lines · 19 tokens per session scan A 2be7cfe121eb
production-readiness 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 5,159 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review-impl
Unbiased review of another session's implementation (diff, staged, or branch).
nyann:explain-diff
Translate a DriftReport JSON (from doctor / retrofit / compute-drift) into a plain-English markdown narrative. Read-only template render with no LLM call — produces paste-friendly output for PR bodies, chat threads, or bug reports.
re-review
Round 2+ review — confirm revisions landed, catch regressions, do not re-litigate.
review-spec
Unbiased review of another session's spec or design doc.
pr
Review a GitHub PR or GitLab MR with Punchcard and post the review into it.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.