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/technical-roadmap)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/technical-roadmap"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/technical-roadmap/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/technical-roadmap"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/technical-roadmap.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 | $0.02699 |
| Opus 5.5 | $0.00006 | $0.01080 |
| Sonnet 5.5 | $0.00003 | $0.00540 |
| Haiku 4.5 | $0.00002 | $0.00270 |
Grade A, and why
technical-roadmap 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 1mo 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:technical-roadmap
Trigger
/architect:technical-roadmap
Purpose
Create a realistic, dependency-aware technical roadmap that sequences work into phases with clear milestones, exit criteria, and resource needs. Goes beyond a simple timeline to include risk gates, parallel workstreams, and decision points.
Workflow
Step 0: Prerequisites
Before doing anything else, check whether sufficient architecture context exists:
- Check if
architecture-output/_state.jsonexists and has atech_stackobject with at least one non-empty field - OR check if
solution.sdl.yaml(orsdl/directory) exists at the project root
If NEITHER condition is met:
"I need an architecture blueprint to generate a technical roadmap — it defines the components, tech stack, and scope that the roadmap is built around. Run
/architect:blueprintfirst, then come back here."
Stop immediately. Do NOT attempt to run blueprint yourself. Do NOT continue.
If at least one condition is met, proceed to Step 1.
Step 1: Gather Context
Read in this order:
architecture-output/_state.json— read first if it exists; useproject,tech_stack,components,entities,personas,mvp_scope,top_risksdirectly — these replace intent.json and SDL for most roadmap decisionsintent.json— only if_state.json.projectis absent; extract vision, constraints, timeline expectations- SDL — only if
_state.json.tech_stackor_state.json.componentsis absent; checksolution.sdl.yamlfirst; if absent, readsdl/README.mdthen the relevant module files. Grep forcomponents:,tech:, andproduct:blocks only — do NOT read the full file architecture-output/problem-validation.md— risk assessment (read in full, typically small)architecture-output/cost-estimate.md— budget constraints (read in full, typically small)architecture-output/data-model.md— only if_state.json.entitiesis absent; if reading, Grep for the header/summary section only to get entity count and domain groupingsarchitecture-output/user-personas.md— only if_state.json.personasis absent; if reading, Grep for persona names and priority onlyarchitecture-output/deep-research.md— only if_state.json.market_researchis absent; if reading, Grep for competitive timeline pressure
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.
- 1mo ago First seen · 255 lines · 15 tokens per session scan A 868ddf27cbb6
technical-roadmap is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 2,699 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
nyann:bootstrap
Explicit entry point for nyann's bootstrap flow. Does exactly what the natural-language trigger ("set up this project") does, but skips intent detection so users who prefer slash commands can opt in directly.
nyann:suggest
Analyze a repository and suggest profile updates based on installed dependencies, config files, repo structure, and git history patterns.
octo-scheduler
Manage the Claude Octopus scheduled workflow runner daemon.
next
Read the active sprint’s current status. Refresh stale compilation using grainulator compile --dir or grainulator.compile. Use the resulting nextactions with the user’s current scope and authorization. Output only the two Auto and Manual lists below, with no recap, status counters or offer to continue. Continue useful…
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
create-task
Create one bounded task contract from a short request or optional structured brief, while routing unambiguous feedback on an existing task back to its defect cycle instead of duplicating work.