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 skills add cat-xierluo/legal-skills --skill multi-agent-orcagit clone --depth 1 https://github.com/cat-xierluo/legal-skillsWrote 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/skills/cat-xierluo/legal-skills/multi-agent-orca)<a href="https://agentmods.dev/skills/cat-xierluo/legal-skills/multi-agent-orca"><img src="https://agentmods.dev/badge/skills/cat-xierluo/legal-skills/multi-agent-orca/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cat-xierluo/legal-skills/multi-agent-orca"><img src="https://agentmods.dev/badge/skills/cat-xierluo/legal-skills/multi-agent-orca.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00132 | $0.12851 |
| Opus 5.5 | $0.00053 | $0.05140 |
| Sonnet 5.5 | $0.00026 | $0.02570 |
| Haiku 4.5 | $0.00013 | $0.01285 |
Grade B, and why
multi-agent-orca scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- 全局配置文件（如 `~/.codex/config.toml`、`~/.codex/hooks.json`、`~/.config/magpie/providers.json`）是跨会话共享写入点，不受 worktree `git status` 保护。写入前必须指定具名单写者、保存私有快照并记录段/键清单；写入后逐项回读 diff，缺段即停（详见 `references/40-codex-app-native-coordinatio The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CHANGELOG.md 280 KB
- config/claude-provider-registry.example.json 1.4 KB
- config/claude-provider-settings.example.json 788 B
- config/codebuddy-auth-first-run.sh 1.3 KB runs code
- config/codex-spark.profile.toml.example 1.6 KB
- config/harness-backend-policy.json 3.0 KB
- config/orchestration-personal.example.json 9.6 KB
- LICENSE.txt 1.1 KB
- references/00-fast-dispatch-runbook.md 4.3 KB
- references/01-model-selection-matrix.md 16 KB
- references/02-runtime-dependencies.md 11 KB
- references/03-checkpoint-files.md 5.7 KB
- references/04-sentinel-design.md 8.8 KB
- references/05-legal-domain-patterns.md 13 KB
- references/06-agent-cli-reference.md 8.3 KB
- references/07-qoderwork-cli-worker.md 591 B
- references/08-codebuddy-cli-worker.md 7.0 KB
- references/09-zcode-cli-worker.md 7.6 KB
- references/10-parallel-lessons.md 9.3 KB
- references/11-agent-teams-troubleshooting.md 3.9 KB
- references/12-issue-grouping.md 11 KB
- references/13-orca-cli-worker.md 26 KB
- references/14-pm-orchestrate.md 29 KB
- references/15-wave-autopilot.md 18 KB
- references/16-autopilot-durability.md 19 KB
- references/17-model-capability-profile.md 7.9 KB
- references/18-dispatch-acceptance-contracts.md 13 KB
- references/19-maintainer-validation.md 12 KB
- references/20-orca-rate-limit-recovery.md 6.2 KB
- references/21-zcode-quota-producer.md 4.9 KB
- references/22-mem-budget-lane.md 25 KB
- references/23-runtime-settlement.md 7.0 KB
- references/24-sub2api-quota-producer.md 8.0 KB
- references/24-zcode-driver-safety.md 10 KB
- references/25-remote-node-dispatch.md 11 KB
- references/26-optional-cli-backends.md 10 KB
- references/27-qwenwork-cli-worker.md 2.6 KB
- references/28-zcode-cli-bigmodel-coding-plan.md 11 KB
- references/29-local-account-routing-skill.md 3.5 KB
- references/30-zcode-native-orca.md 12 KB
- references/31-borrowed-existing-worktree.md 5.8 KB
- references/32-dispatch-profiles.md 4.9 KB
- references/33-pm-continuation-readiness.md 5.7 KB
- references/34-zcode-desktop-remote.md 17 KB
- references/35-zcode-browser-automation.md 14 KB
- references/37-worker-resource-closeout.md 9.2 KB
- references/38-zcode-gui-remote-pr.md 6.8 KB
- references/39-sparse-worktree-dispatch.md 9.4 KB
- references/40-codex-app-native-coordination.md 14 KB
- references/41-pm-merge-and-sync.md 15 KB
- references/zcode-gui-artifacts.md 5.3 KB
- references/zcode-gui-evidence-pipeline.md 6.5 KB
- references/zcode-gui-monitor-adapter.md 8.2 KB
- references/zcode-gui-observe.md 7.8 KB
- references/zcode-recovery-json.md 4.0 KB
- references/zcode-session-evidence.md 5.6 KB
- scripts/acceptance-recovery.py 8.4 KB runs code
- scripts/acceptance-repair-gate.py 27 KB runs code
- scripts/autopilot_runtime.py 77 KB runs code
- scripts/autopilot-controller.py 7.4 KB runs code
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 Changed · +9 lines scan A → B 9d1eec0e74ff
- 9d ago First seen · 293 lines · 132 tokens per session scan A 6d6158e47507
multi-agent-orca is a skill published in the GitHub repository cat-xierluo/legal-skills (754 stars, last pushed today), with no licence file. It adds 132 tokens to every session and 12,851 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…