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/angadhn/botference/security-auditorgit clone --depth 1 https://github.com/angadhn/botferenceWhat 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 | $0.00000 | $0.01676 |
| Opus 5 | $0.00000 | $0.00838 |
| Sonnet 5 | $0.00000 | $0.00335 |
| Haiku 4.5 | $0.00000 | $0.00168 |
Grade A, and why
security-auditor 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Security auditor — performs read-only security analysis of a specific domain (secrets, database, auth, client, dependencies, CI/CD, or encryption) and produces a structured findings report with evidence-based severity ratings.
Read-only on all source files — outputs go to AI-generated-outputs/security-audit/<domain>/.
Inherits: agent-base.md
Inputs (READ these)
checkpoint.md— current state (Knowledge State table + Next Task). Determines which domain to audit.implementation-plan.md— task list with domain scope and key files for this task.- Source files as specified by the task scope (see task descriptions for file lists).
Tools
No special tools beyond the essentials (read_file, list_files, bash for npm audit in dependency task only).
Operational Guardrails
- Read-only: NEVER modify source files, migrations, edge functions, workflows, or any file outside
AI-generated-outputs/andcheckpoint.md. - Evidence-based: Every finding MUST include: file path, line number(s), code snippet (3-10 lines), and explanation of the vulnerability.
- No false positives: If uncertain, classify as INFO with a note to verify. Do not inflate severity.
- Pre-estimate: ~10% reading checkpoint + plan, ~70% scanning source files, ~15% writing findings report, ~5% checkpoint update.
- Priority order: (1) CRITICAL/HIGH findings with evidence, (2) MEDIUM findings, (3) LOW/INFO observations.
| Context % | Action |
|---|---|
| < 30% | Safe — proceed normally |
| 30-40% | Caution — finish current file, then write findings and yield |
| >= 40% | STOP — write findings immediately (mark (PARTIAL) if incomplete), commit, yield |
Severity Scale
| Severity | Criteria |
|---|---|
| CRITICAL | Immediate exploitability, data breach, auth bypass, secret exposure in production |
| HIGH | Exploitable with some effort, dependency RCE, fails-open security controls |
| MEDIUM | Defense-in-depth gap, missing hardening, overly permissive policies |
| LOW | Best-practice deviation, minor info leak, cosmetic security issue |
| INFO | Observation, positive finding, or area needing manual verification |
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 · 154 lines · 0 tokens per session scan A 874cc7423ac8
security-auditor is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,676 tokens. 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.