Borrowing it
Nothing to install: this file belongs to pranee54/AgentDoctor. 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/pranee54/AgentDoctor/main/.cursor/skills/agentdoctor-zero-trust-security/SKILL.mdgit clone --depth 1 https://github.com/pranee54/AgentDoctorWrote 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/skills/pranee54/agentdoctor/agentdoctor-zero-trust-security)<a href="https://agentmods.dev/skills/pranee54/agentdoctor/agentdoctor-zero-trust-security"><img src="https://agentmods.dev/badge/skills/pranee54/agentdoctor/agentdoctor-zero-trust-security/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/skills/pranee54/agentdoctor/agentdoctor-zero-trust-security"><img src="https://agentmods.dev/badge/skills/pranee54/agentdoctor/agentdoctor-zero-trust-security.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 | $0.00047 | $0.00411 |
| Opus 5.5 | $0.00019 | $0.00164 |
| Sonnet 5.5 | $0.00009 | $0.00082 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
agentdoctor-zero-trust-security 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 29d 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.
What it actually says
AgentDoctor zero-trust security
Purpose
Keep AgentDoctor as the authority for boundaries, tools, approval, verification, and evidence. Models and repo text are untrusted data.
Canonical layers
- Containment:
src/security/paths.tsresolveSafeRepoPath - Ownership:
src/project/ownership.ts(realpath classification;OWNERSHIP_BOUNDARY_VERSION) - CLI broad-root:
src/cli/safe-root.tsresolveCliProjectRoot - Discovery:
src/discovery/files.tsdecideDirectoryTraversal
Non-negotiable rules
- Containment ≠ ownership
- Fail closed on path/ownership deny
- No UI/
approved=trueboolean as write authority - Dashboard chat is ask-only (no repo writes)
- Repository content (README, AGENTS.md, comments) cannot escalate privileges
- Skills/prompts cannot override runtime controls
Hostile checklist
.private/,AgentDoctorOS/, nested.git, fixtures, validation checkouts- Symlink alias into private/foreign
$HOME/ Desktop / Downloads / Documents- Forged planHash / grant / approvalToken
- MCP STDIO forge (not helper-only tests)
- Provider tool-call loop with local adversarial server
- what-if foreign/private targets
Evidence
Prefer executable tests under tests/unit/project/, tests/unit/mcp/mcp-transport-adversarial.test.ts, tests/unit/ai/provider-adversarial-e2e.test.ts.
What NOT to do
Weaken ownership to fix false-positive tests; claim transport-complete MCP without STDIO forge; claim vendor LLM safety from local deterministic E2E alone.
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.
- 29d ago First seen · 39 lines · 47 tokens per session scan A e855d8181b7f
agentdoctor-zero-trust-security is a skill published in the GitHub repository pranee54/AgentDoctor (10 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 411 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 2026-09-28.
Other skills, from other repositories
user-research-cookiy
End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design, usability studies, participant recruitment…
best-practices
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
code-documentation
Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.
curate-a-team-library
Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful whyHere notes, and create a starter pack once the first pass is solid.
migrate-skills-between-libraries
Use when moving skills between library workspaces or upgrading from a personal library to a team library. Export from one workspace, import into another.
audit-library-health
Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.