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/eg-checklistgit 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/eg-checklist)<a href="https://agentmods.dev/agents/lukacf/meerkat/eg-checklist"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/eg-checklist.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 | $0.00000 | $0.00530 |
| Opus 5 | $0.00000 | $0.00265 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
EG-checklist 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 6d 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
Lane EG Checklist
-
EG-01DOGMA-20Rebuild or replace the liveproduct_sessionon mob-member websocket rotation. Done when post-rotation traffic uses the new bridge session rather than the retired one. -
EG-02DOGMA-20Reset projection and attachment behavior coherently during rotation. Done when websocket status, input, and commit paths operate against the rotated session after the event. -
EG-03DOGMA-14Remove silentStandaloneEphemeralfallback when runtime-backed authority exists. Done when runtime-backed surfaces recover canonical bindings or fail explicitly instead of degrading silently. -
EG-04DOGMA-14Wire runtime-backed recovery through adjacent surfaces, not just the standard helper path. Done when nearby runtime adapters feed canonical bindings into recovery. -
EG-05DOGMA-23Introduce a typed schedule-domain runtime delivery outcome model. Done when runtime admission and completion meaning is carried into schedule state without surface-local reinterpretation. -
EG-06DOGMA-23Relegate legacy schedule failure classes to derived/read-model output only. Done when canonical schedule persistence stores typed runtime meaning rather than rewritten classes. -
EG-07DOGMA-18Move defaultprojectanduserskill source identities into canonical registry resolution. Done when default sources are not created from helper-local UUID fabrication. -
EG-08DOGMA-18Update REST/RPC session skill canonicalizers to use the same registry path. Done when default-source skill refs resolve through one canonical registry path. -
EG-09DOGMA-18Add or extend a defensive scan banning helper-local UUID fabrication outside the canonical registry path. Done when the scan is checked in and wired for lane/final gating. -
EG-10Self static review. Done whenDOGMA-23is clearly a full typed-outcome fix rather than a relabeled classification helper. -
EG-11Handoff note. Done when handoff commit, changed files, and risks are recorded in EG-plan.md. -
EG-12Generated-output request. Done when any schema/regeneration need is recorded explicitly, or markednone.
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.
- 6d ago First seen · 15 lines · 0 tokens per session scan A c08eb2cd49b3
EG-checklist is an agent published in the GitHub repository lukacf/meerkat (20 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 530 tokens. 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…