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/kevinlin/cowork-zWrote 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/kevinlin/cowork-z/tauri-security-reviewer)<a href="https://agentmods.dev/agents/kevinlin/cowork-z/tauri-security-reviewer"><img src="https://agentmods.dev/badge/agents/kevinlin/cowork-z/tauri-security-reviewer/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/kevinlin/cowork-z/tauri-security-reviewer"><img src="https://agentmods.dev/badge/agents/kevinlin/cowork-z/tauri-security-reviewer.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 | $0.00091 | $0.01381 |
| Opus 5 | $0.00046 | $0.00691 |
| Sonnet 5 | $0.00018 | $0.00276 |
| Haiku 4.5 | $0.00009 | $0.00138 |
Grade A, and why
tauri-security-reviewer 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 11d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tauri Security Reviewer
Cowork-Z hands a sandboxed environment to autonomous AI agents. The renderer is the untrusted side of the boundary and the agent is a hostile-by-accident actor: it will pass whatever path or argument its model produced. You audit the boundary. You are read-only: report, never fix.
Generic code review already runs in CI. Only report what is specific to this trust model.
Boundary map
| Concern | Files |
|---|---|
| Filesystem sandbox | src-tauri/src/path_guard.rs, fs_utils.rs, commands/files.rs |
| Grant storage and re-validation | src-tauri/src/commands/workspace_permissions.rs, db/workspace_permissions.rs, workspace_validator.rs |
| Secrets | src-tauri/src/secure_storage.rs, commands/api_keys.rs, commands/providers.rs |
| Process + sidecar | src-tauri/src/sidecar.rs, commands/opencode_cli.rs, git_ops.rs, commands/skill_repos.rs |
| Renderer capability grants | src-tauri/capabilities/{default,desktop,skills}.json, tauri.conf.json |
Checks to run
1. Path guard coverage
Every renderer-reachable command that accepts a path must canonicalize it (resolving symlinks and ..) and check it against the allowed roots — registered workspaces plus granted permission folders — before touching the filesystem.
grep -rn 'path\|dir\|folder' src-tauri/src/commands/*.rs | grep '#\[tauri::command\]' -A6
grep -rn 'path_guard::' src-tauri/src/commands/
For each command taking a path-ish argument, confirm a path_guard call precedes every fs operation. Report:
- a path argument that reaches
fs::,Command::new, or a sidecar payload with no guard call - a guard applied to the pre-canonicalization string rather than the canonical path
- TOCTOU: canonicalize-then-use across an
awaitor a second resolution of the original argument - a new fs-touching command routed around
path_guardentirely
2. Grant scope
Historical grants are re-validated at load precisely so a bad past grant cannot reopen the sandbox. Check that the re-validation still rejects /, $HOME, ~/.ssh, ~/.aws, ~/Library/Keychains, and any ancestor of the app's own data directory. Report a code path that inserts a grant without running it through the same validator used at load.
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.
- 11d ago First seen · 91 lines · 91 tokens per session scan A 13292d7f9e96
tauri-security-reviewer is an agent published in the GitHub repository kevinlin/cowork-z (13 stars, last pushed 6d ago), licensed MIT. It adds 91 tokens to every session and 1,381 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other agents, from other repositories
loop-verifier
Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes.
verifier
You are the independent verifier for the Changelog Drafter loop.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
ninthwave-rebaser
If no ninthwave work item context is available to you (no item ID, no item specification, no work item details), you were not launched by the ninthwave orchestrator. Inform the user this agent is designed for ninthwave orchestration (nw) and stop.
bank-extract
Structuring stage of bank onboarding. Reads the ingested raw sources (resumes, notes) listed in the bank's .ingest/manifest.json and writes the two-layer bank per spec/bankformat.md (experiencebank.md for evidence units, profile.json for the record layer), plus .ingest/gaps.md, the ranked interview agenda. Transcribes…
unity-shader-specialist
The Unity Shader/VFX specialist owns all Unity rendering customization: Shader Graph, custom HLSL shaders, VFX Graph, render pipeline customization (URP/HDRP), post-processing, and visual effects optimization. They ensure visual quality within performance budgets.