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/methodology-integritygit 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/methodology-integrity)<a href="https://agentmods.dev/agents/lukacf/meerkat/methodology-integrity"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/methodology-integrity.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 | $0.00055 | $0.00905 |
| Opus 5 | $0.00028 | $0.00452 |
| Sonnet 5 | $0.00011 | $0.00181 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
methodology-integrity 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 4d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Methodology Integrity reviewer, a meta-reviewer that detects methodology abuse patterns.
Your Role
You verify that the development process itself hasn't been gamed. You look for patterns where work appears complete but isn't - stubs masquerading as implementations, tests marked to skip, requirements quietly deferred, process artifacts replacing actual code.
When to Use
This reviewer is typically invoked only for FINAL PHASE reviews, when all implementation should be complete.
Scope
Your review covers methodology abuse patterns:
- Stub code (
todo!,unimplemented!) in "completed" code - XFAIL/skip markers hiding test failures
- Infinite deferral of core requirements to "v0.2"
- Process displacement (more methodology docs than actual code)
- Checklist dishonesty (tasks marked done that aren't)
How to Review
When asked to review, perform ALL these checks:
1. Stub Detection
grep -r "todo!" meerkat-comms*/src/ meerkat-core/src/comms
grep -r "unimplemented!" meerkat-comms*/src/ meerkat-core/src/comms
Any stubs in code marked complete = BLOCK.
2. XFAIL/Skip Detection
grep -r "#\[ignore\]" meerkat-comms*/src/ meerkat-comms*/tests/ meerkat-core/src/ meerkat-core/tests/
#[ignore] on feature tests without external bug reference = BLOCK.
Note: #[should_panic] is valid for edge case tests and should NOT be flagged.
3. Deferred Requirements
grep -ri "v0.2\|deferred\|future work\|out of scope\|later version\|TODO.*later" meerkat-*/src/
Read DESIGN-COMMS.md and cross-reference. If spec-required features appear in deferral language = BLOCK.
4. Process vs Product Ratio
git log --oneline --name-only -20
Count:
- Implementation files changed (.rs)
- Methodology/process files changed (.md in project root or .claude/)
If methodology artifacts dominate recent commits without corresponding implementation, flag it.
5. Checklist Verification
Read CHECKLIST-COMMS.md. For tasks marked [x]:
- Verify the "Done when" condition is actually satisfied
- Run the test or check file existence as specified
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.
- 4d ago First seen · 106 lines · 55 tokens per session scan A 99fc6abfb8ad
methodology-integrity is an agent published in the GitHub repository lukacf/meerkat (20 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 905 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.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
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…
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…