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/d2-plangit 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/d2-plan)<a href="https://agentmods.dev/agents/lukacf/meerkat/d2-plan"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/d2-plan.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 | $0.00000 | $0.01537 |
| Opus 5 | $0.00000 | $0.00768 |
| Sonnet 5 | $0.00000 | $0.00307 |
| Haiku 4.5 | $0.00000 | $0.00154 |
Grade A, and why
D2-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 3d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lane D2 Plan
Owned Rows
DOGMA-16DOGMA-24DOGMA-25
Owned Milestones
D2-1=DOGMA-25D2-2=DOGMA-16,DOGMA-24
Owned Files
meerkat-contracts/src/capability/registry.rsmeerkat-skills/src/engine.rsmeerkat-auth-core/src/resolver.rs- provider runtimes:
meerkat-openai/src/runtime/mod.rsmeerkat-anthropic/src/runtime/mod.rsmeerkat-gemini/src/runtime/mod.rs
- capability-aware factory ranges in
meerkat/src/factory.rs
Shared Files Touched Under Round Map
meerkat/src/factory.rsas second owner, afterD1- provider runtime
mod.rsfiles as second owner, afterD1
Blocked By
D2-2blocked byD1-1
Unblocks
- none hard-blocked, but closes auth/runtime policy correctness
Public / Type / Schema Changes
- no public rename surface
- effective capability truth becomes the only skill filtering seed
- external-authorizer flows materialize a real
DynamicLease - policy fields alter resolved runtime behavior
Defensive Scan Commitments
- none mandatory beyond tests for
DOGMA-25, but lane must preserveD1’s identity scan cleanliness
Requested Orchestrator Probes
./scripts/repo-cargo check -p meerkat./scripts/repo-cargo check -p meerkat-skills./scripts/repo-cargo check -p meerkat-contracts./scripts/repo-cargo check -p meerkat-openai./scripts/repo-cargo check -p meerkat-anthropic./scripts/repo-cargo check -p meerkat-gemini
Requested Build Gate Commands
- Quick probe
D2-1:./scripts/repo-cargo check -p meerkat./scripts/repo-cargo check -p meerkat-skills./scripts/repo-cargo check -p meerkat-contracts
- Quick probe
D2-2:./scripts/repo-cargo check -p meerkat-openai./scripts/repo-cargo check -p meerkat-anthropic./scripts/repo-cargo check -p meerkat-gemini./scripts/repo-cargo check -p meerkat./scripts/repo-cargo check -p meerkat-skills
- Full gate
D2-1:./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 --lib --show-progress none --status-level none --final-status-level fail./scripts/repo-cargo e2e-fast
- Full gate
D2-2:./scripts/repo-cargo nextest run -p meerkat-openai --lib --show-progress none --status-level none --final-status-level fail./scripts/repo-cargo nextest run -p meerkat-anthropic --lib --show-progress none --status-level none --final-status-level fail./scripts/repo-cargo nextest run -p meerkat-gemini --lib --show-progress none --status-level none --final-status-level fail./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 --lib --show-progress none --status-level none --final-status-level fail./scripts/repo-cargo e2e-fast
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.
- 3d ago First seen · 125 lines · 0 tokens per session scan A 0bdc3dfc41ba
D2-plan is an agent published in the GitHub repository lukacf/meerkat (20 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,537 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.
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…