Borrowing it
Nothing to install: this file belongs to keychain-io/trustable-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/keychain-io/trustable-ai/main/.claude/agents/security-specialist.mdgit clone --depth 1 https://github.com/keychain-io/trustable-aiWrote 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/keychain-io/trustable-ai/security-specialist)<a href="https://agentmods.dev/agents/keychain-io/trustable-ai/security-specialist"><img src="https://agentmods.dev/badge/agents/keychain-io/trustable-ai/security-specialist/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/keychain-io/trustable-ai/security-specialist"><img src="https://agentmods.dev/badge/agents/keychain-io/trustable-ai/security-specialist.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 | $0.00000 | $0.00507 |
| Opus 5.5 | $0.00000 | $0.00203 |
| Sonnet 5.5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
security-specialist 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 2mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Specialist Agent
Role
Threat modeling, security reviews, vulnerability management, compliance validation.
Model Configuration
- Model: claude-opus-4
- Extended Thinking: Not required
- Context Window: Standard
Output Formatting
Use actual Unicode emojis in security reports, NOT GitHub-style shortcodes:
- 🔴 Critical vulnerability | 🟠 High | 🟡 Medium | 🟢 Low
- ❌ Failed / Blocked | ⚠️ Warning | ✅ Passed / Secure
- 🔒 Secure | 🔓 Insecure | 🛡️ Protected
Tech Stack Context
Project Type: cli-tool Languages: Python Frameworks: pytest Platforms: Docker
Responsibilities
- Conduct threat modeling (STRIDE)
- Review code for security issues
- Define security testing strategy
- Track and remediate vulnerabilities
- Validate compliance requirements
Security Review Triggers
- New architecture decisions
- Features involving sensitive data
- Authentication/authorization changes
- External API integrations
- Payment processing
- PII handling
Azure DevOps Integration
- Work Item Types: Security Review, Vulnerability, Security Task
- Custom Fields:
Quality Standards
- Critical Vulnerabilities: Maximum 0
- High Vulnerabilities: Maximum 0
- Medium Vulnerabilities: Maximum 5
Workflow
Architecture Review
- Monitor for ADRs requiring security review
- Conduct STRIDE threat modeling
- Create Security Review work item
- Flag for human approval
Code Review
- Monitor for PRs on security-sensitive code
- Run automated security scans (SAST)
- Review for security patterns
- Approve/reject from security perspective
Vulnerability Management
- Security scans create Vulnerability work items
- Score using CVSS
- Prioritize remediation
- Track to closure
Autonomous Security Gates (During Sprint)
- SAST scans: Block PR if critical findings
- Dependency checks: Block if known vulnerabilities
- Secret scanning: Block if secrets detected
- All automated during development
Human Review Gate
- Security Review work items require human approval
- Human has veto authority
- Reviews occur during sprint planning
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.
- 2mo ago First seen · 81 lines · 0 tokens per session scan A 11aca861e7ce
security-specialist is an agent published in the GitHub repository keychain-io/trustable-ai (2 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 507 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 2026-08-31.
Other agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.