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/c-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/c-plan)<a href="https://agentmods.dev/agents/lukacf/meerkat/c-plan"><img src="https://agentmods.dev/badge/agents/lukacf/meerkat/c-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 | $0.00827 |
| Opus 5 | $0.00000 | $0.00413 |
| Sonnet 5 | $0.00000 | $0.00165 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
C-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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lane C Plan
Owned Rows
DOGMA-12DOGMA-19
Owned Milestones
C1=DOGMA-12,DOGMA-19
Owned Files
meerkat-comms/src/io_task.rsmeerkat-comms/src/inbox.rsmeerkat-runtime/src/comms_drain.rs- adjacent commit-point helpers if needed:
meerkat-runtime/src/meerkat_machine/comms_drain.rs
Shared Files Touched Under Round Map
- none outside the lane-owned trust seam
Blocked By
- none
Unblocks
- none hard-blocked, but reduces trust/regression risk for the round
Public / Type / Schema Changes
- no public rename surface
- internal ingress/rollback semantics only
- no schema or SDK regen expected
Defensive Scan Commitments
- add or update a scan banning:
- trust publication before DSL bind/authorize commit
- ack-before-final-admission behavior
- dual ownership of ingress trust decisions
- fulfilled in lane-owned regression tests inside:
meerkat-comms/src/io_task.rsmeerkat-comms/src/inbox.rsmeerkat-runtime/src/comms_drain.rs
Requested Orchestrator Probes
./scripts/repo-cargo check -p meerkat-comms./scripts/repo-cargo check -p meerkat-runtime
Requested Build Gate Commands
- Quick probe:
./scripts/repo-cargo check -p meerkat-comms./scripts/repo-cargo check -p meerkat-runtime
- Full gate:
./scripts/repo-cargo nextest run -p meerkat-comms --lib --show-progress none --status-level none --final-status-level fail./scripts/repo-cargo nextest run -p meerkat-runtime --lib --show-progress none --status-level none --final-status-level fail./scripts/repo-cargo e2e-fast
Risks
- row
12and19are one semantic seam and must stay commit-first, trust-second - handler rollback paths are easy to leave half-correct without explicit tests
Open Decisions
- none
Handoff Notes
- handoff commit: none
- changed files:
meerkat-comms/src/io_task.rsmeerkat-comms/src/inbox.rsmeerkat-runtime/src/comms_drain.rs.rct/round5/agents/C-checklist.md.rct/round5/agents/C-plan.md
- generated output request: none
- known risks:
- cargo checks/tests not run in-lane per instruction; orchestrator should run the requested probes before merge
- defensive scan is implemented as owned regression tests rather than a new top-level script to stay within lane-owned file scope
- INT quick probe found and this lane fixed one compile issue:
SupervisorBindingStageErrorimport had been test-gated while rollback helpers use it in production code; re-probe requested - full gate found and this lane fixed one test compile issue:
meerkat-comms/src/io_task.rstest module neededInboxItemimported back into scope; re-probe/full-gate rerun requested - full gate then found two stale
io_tasktest expectations that still assumed untrusted ingress returnedOk(()); this lane updated them to assertErr(IoTaskError::IngressDropped(DropReason::UntrustedSender)) - full gate then found one borrow/move issue in the new rollback coverage:
bind_member_rolls_back_binding_when_trust_publication_failsnow clones the sender peer id before movingpayloadintoBridgeCommand::BindMember
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 · 90 lines · 0 tokens per session scan A 1a7233f97315
C-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 827 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…