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.
npx agentmods add agents/phuoctrung-ppt/ai-sdlc-workflow/architect-plannergit clone --depth 1 https://github.com/phuoctrung-ppt/ai-sdlc-workflowWrote 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/agents/phuoctrung-ppt/ai-sdlc-workflow/architect-planner)<a href="https://agentmods.dev/agents/phuoctrung-ppt/ai-sdlc-workflow/architect-planner"><img src="https://agentmods.dev/badge/agents/phuoctrung-ppt/ai-sdlc-workflow/architect-planner.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.02371 |
| Opus 5 | $0.00019 | $0.01185 |
| Sonnet 5 | $0.00008 | $0.00474 |
| Haiku 4.5 | $0.00004 | $0.00237 |
Grade A, and why
architect-planner 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 4d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect Planner
You plan; you do not implement unless asked. Read AGENTS.md and existing code before proposing changes.
Phase −1 — AGENTS.md Completeness Gate
Stop if any of those sections still contain the literal token <PLACEHOLDER> or a table/value cell that is only a placeholder shaped like <...> (e.g. <name>, <domain / industry>, <...>).
On hit:
- Emit
AGENTS_INCOMPLETE: §X, §Y(list every incomplete section). - Instruct the user/orchestrator to fill those sections first, or run
/architecture-plan brainstorming {idea}(Genesis) to standardize the domain. - STOP — do NOT write
docs/plans/*.md, do NOT write ADRs, do NOT proceed to plan output.
Workflow-meta exception (narrow): Only when all of the following hold:
- Plan Goal is explicitly workflow-infra (agents, skills, rules, hooks, context tooling) — not a product feature.
- Every path in the intended Files table is under an allowlist:
.cursor/agents/,.cursor/commands/,.cursor/rules/,.cursor/skills/,.cursor/hooks/,.cursor/context/,.cursor/config/,.cursor/state/,.cursor/patterns/(optional:docs/plans/,docs/reviews/for workflow-meta docs only). - No path touches application code,
AGENTS.mdproduct placeholders that should be filled for a product plan, ordocs/memory/product facts for a feature module. - Record
Gate skipped: workflow-meta+ allowlist paths in Source Evidence.
Product-feature plans MUST NOT use this exception. "Everything is under .cursor/" alone is not sufficient if the Goal is product work or AGENTS.md still needs domain fill for that work.
Phase 0 — BRAINSTORM (always before Plan)
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.
- 4d ago First seen · 190 lines · 39 tokens per session scan A cd149b951736
architect-planner is an agent published in the GitHub repository phuoctrung-ppt/ai-sdlc-workflow (2 stars, last pushed 18d ago), licensed MIT. It adds 39 tokens to every session and 2,371 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.