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 commands/dinhnguyenngoc/spec-driven-claude-code/scangit clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-codeWrote 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/dinhnguyenngoc/spec-driven-claude-code/scan)<a href="https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/scan"><img src="https://agentmods.dev/badge/commands/dinhnguyenngoc/spec-driven-claude-code/scan.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 | $0.00009 | $0.04573 |
| Opus 5 | $0.00005 | $0.02286 |
| Sonnet 5 | $0.00002 | $0.00915 |
| Haiku 4.5 | $0.00001 | $0.00457 |
Grade B, and why
scan scanned grade B with 1 finding 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
| **SSRF** | Code path fetches user-supplied URL (URL preview, webhook, image proxy, RSS, OAuth callback) | Integration test DI-resolve REAL fetcher, attempt: `127.0.0.1`, RFC1918 (`10.x`, `192.168.x`, `172.16.x`), `169. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/scan — Security Scan
"Trust but verify."
Purpose
Comprehensive security scan of completed code before deployment. Detect vulnerabilities, insecure dependencies, and security misconfigurations.
Workspace Mode: if the session root declares
Mode: workspace→ resolve the target repo perCLAUDE.md§Workspace Mode before anything else; every path, probe, and gate below is relative to the target repo, and the workspace disk-check applies at the gate.
Prerequisites
Required:
- Code implementation complete (
/builddone) - Tests passing (
/testdone)
Optional (if available):
- Code review approved (
reports/CODE_REVIEW.mdfrom/review)
Quick reference: references/security-checklist.md — pre-deploy security verification checklist (cross-check before composing SCAN_REPORT).
Automation script (already prepared — the agent does NOT run each tool manually):
.claude/scripts/scan-all.sh— runs every available scanner, with a fallback if one is missing.claude/scripts/scan-summarize.py— merges output →security/SCAN_SUMMARY.json
Workflow
Time-optimization principle: The entire tooling execution (gitleaks, semgrep, dotnet vuln, npm audit, trivy, hadolint, ESLint, XSS grep, secrets grep, Roslyn analyzers) is already scripted. The agent runs just 1 command and reads 1 summary file instead of typing ~25 commands sequentially.
The part that NEEDS the agent's brain (not automated): STRIDE re-evaluation matrix + Finding triage + Approval narrative. These are Phase 2–4 below.
Phase 0: Run Automation Script (a single command)
bash .claude/scripts/scan-all.sh
Script architecture: Phase 1 inventory + auto-detect stack → Phase 2 universal (secrets) → Phase 3 dispatch per-stack via auto-discovered plugins in
scripts/scanners/*.sh(currently dotnet, nodejs, python, php, docker — extend by addingscanners/<stack>.shwith ascan_<stack>()function) → Phase 4 summarize. The list below is the union of scans that may run; any step that does not match the detected stack is skipped automatically.
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 · 334 lines · 9 tokens per session scan B 88bff93186f9
scan is a command published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 4,573 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
brooks-audit
Run a Brooks-Lint architecture audit.
kiro-validate-design
Command "kiro-validate-design" from gotalab/cc-sdd, covering technical design validation, core task, execution steps, important constraints and tool guidance.
sdd-setup
Onboarding wizard — DocLanguage, Memory Bank, architecture snapshot, working agreements (quality gate, TDD working mode).
verify
Perform a non-destructive post-implementation verification gate validating the implementation against spec.md, plan.md, tasks.md, and constitution.md.
fix
⚡⚡ Analyze and fix small issues [AUTO DETECT COMPLEXITY].
extend
Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.