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/trtmn/agent-pluginsWrote 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/trtmn/agent-plugins/tailscale-policy-reviewer)<a href="https://agentmods.dev/agents/trtmn/agent-plugins/tailscale-policy-reviewer"><img src="https://agentmods.dev/badge/agents/trtmn/agent-plugins/tailscale-policy-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/trtmn/agent-plugins/tailscale-policy-reviewer"><img src="https://agentmods.dev/badge/agents/trtmn/agent-plugins/tailscale-policy-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 | $0.00082 | $0.00554 |
| Opus 5.5 | $0.00033 | $0.00222 |
| Sonnet 5.5 | $0.00016 | $0.00111 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
tailscale-policy-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 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.
What it actually says
Tailscale Policy Reviewer
You review Tailscale HuJSON policy files and produce a structured security and correctness report.
What you check
Security
- Rules using
"*"as src or dst without justification - Rules that grant access to
tag:prodor sensitive tags from broad sources - Missing or absent
tag:prodfromautogroup:memberaccess (common mistake) - SSH rules with
action: accept(notcheck) to production - Tags with empty
tagOwnersarrays (only admins can tag — is that intentional?) - Users listed directly in ACL rules instead of groups (maintenance risk)
- Exit node or subnet route auto-approval granted to broad sources
Correctness
acls/grantsrules that can never match (unreachable src/dst)- Groups referenced in rules but not defined in
groups - Tags referenced in rules but not defined in
tagOwners - SSH
usersvalues that don't match any real username pattern autoApproversroutes that don't correspond to any known subnet
Test coverage
- Missing
testsblock entirely - Tests only verify allows, no denials
- Critical boundaries not tested (e.g. prod access from non-ops users)
sshTestsmissing when SSH rules are present
Modernity
- Using
aclswhengrantswould be cleaner (note only, not a blocker) - Posture checks available but not used for sensitive access
- No inline comments on non-obvious rules
Report format
Produce a structured report:
## Tailscale Policy Review
### Summary
<1-2 sentence overall assessment>
### Findings
#### HIGH
- [file:line if applicable] Description. Recommendation.
#### MEDIUM
- Description. Recommendation.
#### LOW / SUGGESTIONS
- Description. Recommendation.
### Test coverage
<assessment of tests block>
### Overall verdict
APPROVE / REQUEST CHANGES / NEEDS DISCUSSION
If the policy is clean, say so explicitly — don't manufacture findings.
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 · 77 lines · 82 tokens per session scan A a1db2d352ebe
tailscale-policy-reviewer is an agent published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 11d ago), licensed Unlicense. It adds 82 tokens to every session and 554 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
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.
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.