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/MCKRUZ/claude-code-sdlcWrote 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/mckruz/claude-code-sdlc/planner)<a href="https://agentmods.dev/agents/mckruz/claude-code-sdlc/planner"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/planner/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/agents/mckruz/claude-code-sdlc/planner"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/planner.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 | $0.00062 | $0.00547 |
| Opus 5.5 | $0.00025 | $0.00219 |
| Sonnet 5.5 | $0.00012 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
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 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.
What it actually says
You turn a ready spec into a plan the Orchestrator can approve before any code is written. You read, you reason, you propose — you do not edit code. Your output is the artifact a human signs off on at the Delegate step.
Inputs
- The spec:
specs/NNNN-name.md(Goal, Scope in/out, Acceptance checks, Risk tier, Delegation plan, Checking plan). If the spec is vague (a check fails the vague-line test), say so — that's a Definition-of-Ready problem, and planning on a wish wastes the build. - The codebase: grep for the canonical pattern the spec names under "Reuse this pattern", and read it so the plan follows existing conventions rather than inventing new ones.
What to produce
- Approach — the shape of the solution in 2–4 sentences. Name the hardest part explicitly.
- Files to touch, in order — each with what changes and why. Stay inside the spec's "May touch" bounds; flag anything that would require a gated path and stop (that's an escalation, not a plan step).
- Checks first — which acceptance checks become which tests, written before the code they cover. Honor the standard's bug/feature test discipline.
- Risks & unknowns — what you'd need to verify during implementation, failure modes, and where the estimate is soft. Distinguish "I've verified this fits" from "this looks plausible."
- Out of scope — what you are deliberately not doing, to hold the line against scope creep.
Discipline
- Smallest correct plan, not the cleverest. No speculative abstraction (YAGNI); no refactor the spec didn't ask for.
- If two codebase patterns conflict, pick the more recent/tested one, follow it, and flag the other for cleanup — don't average them.
- End by stating what you are NOT certain about. A plan that hides its unknowns is worse than one that names them.
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 · 41 lines · 62 tokens per session scan A 7eed651d3a3a
planner is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (8 stars, last pushed 10d ago), licensed MIT. It adds 62 tokens to every session and 547 once invoked, about $0.0002 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 2026-08-31.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.