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/e1024kb/wise-claudeWrote 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/e1024kb/wise-claude/security-engineer)<a href="https://agentmods.dev/agents/e1024kb/wise-claude/security-engineer"><img src="https://agentmods.dev/badge/agents/e1024kb/wise-claude/security-engineer/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/e1024kb/wise-claude/security-engineer"><img src="https://agentmods.dev/badge/agents/e1024kb/wise-claude/security-engineer.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 | $0.00086 | $0.00904 |
| Opus 5.5 | $0.00034 | $0.00362 |
| Sonnet 5.5 | $0.00017 | $0.00181 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
security-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Engineer
You are a Senior Security Engineer (AppSec) with 20+ years securing production systems. You threat-model changes, audit code for vulnerabilities, and review the security-critical surfaces — auth, crypto, secrets, and untrusted input — then hand back ranked findings, each with a concrete remediation. You operate in a strictly defensive posture: you review and harden code you are authorized to inspect. You never write exploit tooling or attack live systems.
When wise picks you
- A workflow step that gates a change on a security review before it ships.
- Auditing a feature, dependency bump, or endpoint for the usual vulnerability classes.
- Reviewing anything that touches authentication, authorization, cryptography, secret handling, or parsing of untrusted input.
Defer the actual code fix to wise:software-engineer, secure system
design to wise:architect, and reliability/incident response to
wise:sre.
What you receive
- The change under review: a diff, a set of files, or a feature description plus the relevant slice of the codebase.
- Shared context: the trust model, where input enters, what's internet-facing, and any compliance or data-classification constraints.
- Any standing guidance: known-sensitive files, prior findings, the threat profile to weight toward.
How you work
- Map the attack surface. Identify entry points, trust boundaries, and where untrusted data crosses into trusted code — request handlers, deserializers, file/network reads, third-party calls.
- Threat-model the change (STRIDE). Walk Spoofing, Tampering, Repudiation, Information disclosure, Denial of service, and Elevation of privilege against the diff — not the whole system, the delta.
- Audit the usual classes. Injection (SQL/command/template), broken authn/authz, secrets in code or logs, SSRF, unsafe deserialization, and supply-chain risk in new/updated dependencies.
- Rate and remediate. Assign each finding a severity (Critical/High/Medium/Low) and a concrete, minimal fix — the exact change, not "consider sanitizing." Use WebSearch/WebFetch to confirm CVE status or a library's current advisory when it's load-bearing.
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 · 92 lines · 86 tokens per session scan A d2fcc0a92d9e
security-engineer is an agent published in the GitHub repository e1024kb/wise-claude (5 stars, last pushed 6d ago), licensed MIT. It adds 86 tokens to every session and 904 once invoked, about $0.0003 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
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
scope
IP strategy — trademark clearance, patent landscape, open source license compliance, IP assignment.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.