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/deep-research)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/deep-research"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/deep-research/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/deep-research"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/deep-research.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 | $0.00015 | $0.03022 |
| Opus 5 | $0.00008 | $0.01511 |
| Sonnet 5 | $0.00003 | $0.00604 |
| Haiku 4.5 | $0.00002 | $0.00302 |
Grade A, and why
deep-research 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:deep-research
Trigger
/architect:deep-research — run at any stage, ideally early in the project lifecycle.
Purpose
Conduct systematic web-based research to produce a verified market analysis with real competitor data, sourced market sizing, feature comparison matrices, and opportunity identification. Replaces guesswork with web-verified intelligence. Essential for pitch decks, investor conversations, and product positioning.
Workflow
Step 1: Understand the Product
Read in this order — stop as soon as you have enough to determine the product category:
-
architecture-output/_state.json— read first if it exists. Use directly:project.name,project.description→ product name and categoryproject.type→ app / agent / hybrid (shapes competitor search)- If
_state.jsonhas these fields, skip reading SDL andintent.jsonentirely
-
intent.json— only if_state.jsonis absent or missingproject.description; extract name, vision, target users -
SDL — only if both above are absent; check
solution.sdl.yamlfirst; if absent, readsdl/README.mdthen the relevant module files. Grep forproduct:block only
If nothing exists, use the project directory name as the product name.
Determine the product category for research queries (e.g., "collaborative whiteboard", "HIPAA-compliant messaging", "project management tool").
Step 2: Load Skills
Load:
- deep-research skill — for structured web research methodology (Discover → Verify → Synthesize)
- founder-communication skill — for plain English output
Step 3: Phase 1 — Discover (Broad Search)
Use WebSearch to conduct the following searches:
Competitor discovery (run at least 4 searches):
"{product category}" alternatives"{product category}" competitors 2025"best {product category}" software tools"{product category}" vs(auto-complete reveals top competitors)
Market sizing (run at least 3 searches):
"{product category}" market size 2025 2026"{product category}" TAM SAM SOM"{broader industry}" market report forecast
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 · 302 lines · 15 tokens per session scan A f62768d6fe4a
deep-research is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 3,022 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.