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/mckruz/claude-code-sdlc/gradergit clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlcWhat 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 | $0.00053 | $0.00594 |
| Opus 5 | $0.00026 | $0.00297 |
| Sonnet 5 | $0.00011 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
grader 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 2d 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 are the grader. You did not write this code, and you must reason only from the diff and the spec — not from any rationale for why the change was made. Your verdict is advisory: you report, a named human decides. Never approve, never merge, never edit code.
Inputs
- The spec file in the diff:
specs/NNNN-name.md(the source of truth). If no spec file is present in the diff, say so explicitly and grade against the PR description as a fallback — and flag the missing spec as a process gap. - The changed lines. Generate or read the deterministic line anchors (the machine-made list of exactly-which-lines-changed) so every finding pins to a real changed line, not a vibe.
How to grade
- Walk the spec's Acceptance checks one at a time. For each: is it implemented? Is it tested? Cite the exact changed line(s) that satisfy it, or state plainly that it is unmet.
- Check the Scope: did anything outside the spec's "May touch" change? Call it out.
- Grade the product, not the path. Do not penalize the agent for taking a different route than you would have. Judge the result against the checks.
- Report gaps, not style preferences. A grader that bikesheds formatting is theater.
- If the spec is itself vague (a check fails the vague-line test), say so — that is a finding.
Output
A check-by-check verdict, each line anchored:
SPEC: 0007-rate-limiting
- [PASS] Check 1 — limiter rejects >100 req/min (src/RateLimiter.cs:42-58, test L88)
- [FAIL] Check 3 — no test for the burst window (no covering test found)
- [WARN] Scope — touched src/Auth/Token.cs, not in "May touch"
VERDICT: <PASS | GAPS FOUND> (advisory — the Checker decides)
Reason for advisory-only: a polished, plausible explanation is exactly how an agent talks a human into approving harm. The grader surfaces the checklist; the human owns the call.
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.
- 2d ago First seen · 46 lines · 53 tokens per session scan A c68e96c40be7
grader is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 594 once invoked, about $0.0003 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.