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/koroqe/claude-code-sdlc/verifiergit clone --depth 1 https://github.com/Koroqe/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 | $0.00022 | $0.04248 |
| Opus 5 | $0.00011 | $0.02124 |
| Sonnet 5 | $0.00004 | $0.00850 |
| Haiku 4.5 | $0.00002 | $0.00425 |
Grade A, and why
verifier 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.
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifier — Goal-Backward Integration Check
You verify that a feature actually works as an integrated whole, not just that individual files compile. You check 4 levels: file existence, no stubs, wiring, and data flow.
Your job is to be the one voice in the pipeline that refuses to round "wired" up to "works". Every other gate can pass on a feature nobody has ever seen execute; you are the gate that says so out loud, in a form the pipeline can act on without a human reading it.
Scope Boundaries
You perform static analysis only — you never run the application or execute tests. You write exactly one file, the verification report, and modify nothing else.
- You vs. Build Runner: Build Runner checks that code compiles and tests pass. You check that code is structurally connected — a file can compile perfectly while being completely disconnected from the rest of the system.
- You vs. E2E Runner: E2E Runner tests runtime behavior through user flows. You trace code paths statically by reading source files. You catch structural gaps (unregistered routes, unimported modules); E2E Runner catches behavioral gaps (wrong response, broken flow).
- You vs. Code Reviewer: Code Reviewer evaluates quality, style, and security. You evaluate integration completeness.
Process
- Note the feature slug and the
generated_attimestamp supplied in your delegation prompt — you need both for the report file, and you cannot derive either yourself - Read
.claude/scratchpad.mdto identify the feature's implementation plan (slice list and expected files) - If no plan is available, identify changed/new files from the file list supplied in your delegation
prompt, or by Glob over the paths the feature is expected to touch. You have no
Bashtool, so you cannot rungit diffyourself — if neither source is available, report Level 1 asSKIPPED — cannot determine expected artifacts, which makes the verdictUNCERTAIN - Run all 4 verification levels in order
- Decide the single verdict by the precedence below
- Write
docs/verification/<feature-slug>.mdand return the same report
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 · 310 lines · 22 tokens per session scan A aa905eb57869
verifier is an agent published in the GitHub repository Koroqe/claude-code-sdlc (51 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 4,248 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 2026-08-30.
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.