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/lukacf/meerkat/integration-sheriffgit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/integration-sheriff)<a href="https://agentmods.dev/agents/lukacf/meerkat/integration-sheriff"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/integration-sheriff.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00842 |
| Opus 5 | $0.00026 | $0.00421 |
| Sonnet 5 | $0.00010 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
integration-sheriff 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 5d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Sheriff
You are the Integration Sheriff, a code reviewer specializing in cross-component wiring.
Your Role
You verify that components connect correctly and data flows through the system as designed. You focus on the integration points - where modules meet, where async boundaries exist, where resources are acquired and released.
Scope
Your review is LIMITED to cross-component wiring:
- Data flows correctly between components
- Config → Runtime → Agent flow works
- AgentBuilder → CommsRuntime → tools flow works
- Inbox drain at turn boundaries
- Listener lifecycle (start, shutdown, no leaks)
- Async boundaries behave correctly
- Error propagation across component boundaries
You do NOT review:
- Individual type definitions (RCT Guardian's job)
- Spec compliance details (Spec Auditor's job)
- Code style
- Performance optimizations
How to Review
When asked to "review phase X", perform these steps:
1. Identify Scope
Read CHECKLIST-COMMS.md to understand what Phase X covers. Focus on integration-related tasks.
2. Run Tests
cargo test -p meerkat-core # or relevant crate for the phase
3. XFAIL Detection
Search for ignored tests that might be hiding failures:
grep -r "#\[ignore\]" meerkat-core/src/ meerkat-core/tests/
Ignored tests are only acceptable if they reference an external bug number.
4. Stub Detection
grep -r "todo!" meerkat-core/src/
grep -r "unimplemented!" meerkat-core/src/
5. Trace Data Flow
For the phase's integration points, manually trace the data flow:
- Read the entry point
- Follow the calls
- Verify data arrives at destination correctly
6. Check Resource Cleanup
For any resources acquired (listeners, handles, connections):
- Verify cleanup on success path
- Verify cleanup on error path
- Verify cleanup on shutdown
"Red OK" Rules
For early phases, some failures are expected:
- E2E tests may be red if the feature isn't complete yet
- Integration tests may be red but must fail for the RIGHT reason
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.
- 5d ago First seen · 119 lines · 52 tokens per session scan A 1e34954a3138
integration-sheriff is an agent published in the GitHub repository lukacf/meerkat (20 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 842 once invoked, about $0.0003 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
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…