A work plan for the EG lane of Meerkat, a Rust-based system for running AI agents. It assigns tasks and milestones for session recovery, scheduling, realtime communication, skill selection, and related runtime behavior.

It helps coordinate changes to persistent sessions, recovery, schedules, WebSocket behavior, runtime builders, and the default source used for skills.

It makes dependencies between implementation areas visible, including work that must happen before another lane can continue.

EG-plan — Agent for coding agents by lukacf: A work plan for the EG lane of Meerkat…

Install

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.

agentmods

npx agentmods add agents/lukacf/meerkat/eg-plan

Clone the repo

git clone --depth 1 https://github.com/lukacf/meerkat

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/lukacf/meerkat/eg-plan.svg)](https://agentmods.dev/agents/lukacf/meerkat/eg-plan)

Your own site

<a href="https://agentmods.dev/agents/lukacf/meerkat/eg-plan"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/eg-plan.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,739 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.01739
Opus 5	$0.00000	$0.00870
Sonnet 5	$0.00000	$0.00348
Haiku 4.5	$0.00000	$0.00174

Measured 4d ago against content hash df61c4439352, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

EG-plan 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.

.rct-0.5-archive/round5/agents/EG-plan.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lane EG Plan

Owned Rows

DOGMA-14
DOGMA-18
DOGMA-20
DOGMA-23

Owned Milestones

EG1a = DOGMA-20
EG1b = DOGMA-14, DOGMA-23
EG2 = DOGMA-18

Owned Files

meerkat-session/src/persistent.rs
meerkat-core/src/session_recovery.rs
meerkat/src/surface/runtime_backed.rs
meerkat-mob/src/runtime/builder.rs
meerkat-mob/src/runtime/session_service.rs
meerkat-rpc/src/realtime_ws.rs
meerkat/src/surface/schedule_host.rs
meerkat-skills/src/resolve.rs

Shared Files Touched Under Round Map

meerkat-rpc/src/realtime_ws.rs as first owner for EG1a
meerkat-rest/src/lib.rs as second owner only for EG2, after B1
meerkat-rpc/src/session_runtime.rs as second owner only for EG2, after B1
meerkat-rpc/src/handlers/session.rs as second owner only for EG2, after B1

Blocked By

EG2 blocked by B1

Unblocks

B2 after EG1a

Public / Type / Schema Changes

DOGMA-20 changes websocket/product-session behavior, not public naming
DOGMA-23 is a full schedule-domain typed outcome fix and may require schema freshness work
DOGMA-18 changes canonical default skill-source identity resolution

Defensive Scan Commitments

add or update a scan banning helper-local UUID fabrication for default skill sources outside the canonical registry path

Requested Orchestrator Probes

./scripts/repo-cargo check -p meerkat-rpc
./scripts/repo-cargo check -p meerkat-mob
./scripts/repo-cargo check -p meerkat-session
./scripts/repo-cargo check -p meerkat-core
./scripts/repo-cargo check -p meerkat-schedule
./scripts/repo-cargo check -p meerkat
./scripts/repo-cargo check -p meerkat-skills
./scripts/repo-cargo check -p meerkat-rest
if schedule/public artifacts change:
- make regen-schemas
- make verify-schema-freshness

Requested Build Gate Commands

Quick probe EG1a:
- ./scripts/repo-cargo check -p meerkat-rpc
- ./scripts/repo-cargo check -p meerkat-mob
Quick probe EG1b:
- ./scripts/repo-cargo check -p meerkat-session
- ./scripts/repo-cargo check -p meerkat-core
- ./scripts/repo-cargo check -p meerkat-schedule
- ./scripts/repo-cargo check -p meerkat
- make regen-schemas
- make verify-schema-freshness
Quick probe EG2:
- ./scripts/repo-cargo check -p meerkat-skills
- ./scripts/repo-cargo check -p meerkat-rpc
- ./scripts/repo-cargo check -p meerkat-rest
Full gate EG1a:
- ./scripts/repo-cargo nextest run -p meerkat-rpc --lib --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo nextest run -p meerkat-rpc --test realtime_ws_protocol --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo nextest run -p meerkat-mob --test member_realtime_bindings --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo e2e-fast
Full gate EG1b:
- ./scripts/repo-cargo nextest run -p meerkat-session --lib --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo nextest run -p meerkat-session --test regression_lifecycle --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo nextest run -p meerkat-schedule --lib --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo nextest run -p meerkat --lib --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo e2e-fast
Full gate EG2:
- ./scripts/repo-cargo nextest run -p meerkat-skills --lib --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo nextest run -p meerkat-core --test skill_identity_migrations --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo nextest run -p meerkat-rpc --lib --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo nextest run -p meerkat-rest --lib --show-progress none --status-level none --final-status-level fail
- ./scripts/repo-cargo e2e-fast

Read the full file on GitHub · 136 lines

Changes

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 · 136 lines · 0 tokens per session scan A df61c4439352

Subscribe to this mod's changes

EG-plan 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 1,739 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.

Planning agentic ai ai-agents claude claude-code cli

generate_agent

Generates a customized agent based on user-defined parameters.

ai-driven-dev/framework · 14 tokens

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。.

agents-universe/agents-universe · 33 tokens

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.

Arch1eSUN/Arcgentic · 53 tokens

vc-innovate-agent

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

withkynam/vibecode-pro-max-kit · 32 tokens

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…

wasintoh/toh-framework · 85 tokens

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…

BlackBeltTechnology/pi-agent-dashboard · 98 tokens