Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install dev-workflowsWrote 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/ihudak/ihudak-claude-plugins/vuln)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/vuln"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/vuln/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/commands/ihudak/ihudak-claude-plugins/vuln"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/vuln.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 | $0.00038 | $0.12723 |
| Opus 5.5 | $0.00015 | $0.05089 |
| Sonnet 5.5 | $0.00008 | $0.02545 |
| Haiku 4.5 | $0.00004 | $0.01272 |
Grade A, and why
vuln 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 23d 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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix security vulnerabilities: $ARGUMENTS
Core references. A citation of the form workflows-core:<name> names a shared reference in the workflows-core plugin. Load it with Skill(skill: "workflows-core:reference", args: "<name>") — never by path: ${CLAUDE_PLUGIN_ROOT} resolves to this plugin, which does not carry it.
Each argument token is either ADDRESS:CVE-ID (e.g. PROJ-2423:CVE-2023-46604) or a bare CVE-ID (e.g. CVE-2023-46604). Parse and filter each token, research all CVEs first, then fix them one at a time.
Step 0 — Classify & Route (mandatory)
Invoke the model-routing skill (Skill tool, skill: "workflows-core:model-routing") to load the classification rules, then classify per CVE, based on the size of the required repository change — not the CVE category alone.
Default heuristics:
| Required fix (from research output) | Classification |
|---|---|
| Patch or same-major minor bump, no source-code changes expected | MODERATE |
| Major version bump, or code changes required to adopt the new version | SIGNIFICANT |
| Major bump of a security-critical library, or code changes in auth/session/token/permission/payment/audit paths | HIGH-RISK |
Because the required fix is not known up front, start with a provisional MODERATE routing block for research, then finalize the classification from the research report before fix application begins.
Specs-repo preflight. Invoke Skill(skill: "workflows-core:reference", args: "specs-repo-git specs-preflight") and execute its specs-preflight entry point (§3) inline: flush any leftover session artifacts from an earlier run, retry an artifact commit that failed to push, and settle the branch. This runs against $SPECS_PATH only — git -C "$SPECS_PATH", never a cd, so the code repo this run is about to branch and fix is untouched (§1 rule 1). Prompt-free and silent when the specs repo is clean and on its default branch. If a guard fires, emit its §5 notice; if it returns specs_git: blocked (§3.3 G0), carry that flag for the whole run — the terminal commit-artifacts step skips on it.
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.
- 23d ago Changed 7bfc4ce18df6
- 24d ago Changed · +45 lines 83743c5c60d9
- 28d ago Changed · +23 lines 3256e7ec7924
- 1mo ago Changed · +1 lines 5b3d496340ed
- 1mo ago Changed · +2 lines d465ca1e42e7
- 1mo ago First seen · 329 lines · 38 tokens per session scan A 8ccc0b978e51
vuln is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 24d ago), licensed MIT. It adds 38 tokens to every session and 12,723 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 2026-09-05.
Other commands, from other repositories
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
commit
Context-aware Git commit assistant with smart pre-commit checks.
infogenius
Research-First Image Generation - Facts → Visual Prompt → High-Quality Image.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
watch
You are executing the /hydra:watch command. Live monitoring of all background agents with real-time status updates.