Borrowing it
Nothing to install: this file belongs to qingshihuan/qing-agent-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/qingshihuan/qing-agent-orchestrator/main/.agents/skills/qing-agent-orchestrator-full/SKILL.mdgit clone --depth 1 https://github.com/qingshihuan/qing-agent-orchestratorWrote 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/qingshihuan/qing-agent-orchestrator/qing-agent-orchestrator-full)<a href="https://agentmods.dev/skills/qingshihuan/qing-agent-orchestrator/qing-agent-orchestrator-full"><img src="https://agentmods.dev/badge/skills/qingshihuan/qing-agent-orchestrator/qing-agent-orchestrator-full/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/qingshihuan/qing-agent-orchestrator/qing-agent-orchestrator-full"><img src="https://agentmods.dev/badge/skills/qingshihuan/qing-agent-orchestrator/qing-agent-orchestrator-full.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 | $0.00026 | $0.00523 |
| Opus 5.5 | $0.00010 | $0.00209 |
| Sonnet 5.5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
qing-agent-orchestrator-full 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 1mo 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qing — single owner (experimental)
Qing decides Direct/Lite/Full: compatibility labels, not team templates.
Direct fast path
Current capable parent does the whole task now. For Direct, do not preload references or schemas, call dispatch/start/doctor/models, or emit a routing-only reply. Read, implement and verify. Record the route in the result, not a separate model round. Unknown benefit defaults Direct without an estimator call. Multiple files, offline money/transaction logic, cross-module scope, transport and possible parallelism alone never require Full or a Reviewer.
Whole-task transfer only
Transfer only a substantial complete deliverable with fixed scope and acceptance; one worker implements, debugs and tests it. Parent does not keep half the work, spawn a manager, read live transcripts or poll unchanged progress. Send the contract once; wait for terminal result or a real blocker, then independently verify. Read Single-owner execution only for transfer. Native parent requests still cost tokens; no host request cap is enforced by this skill.
Verification is separate
Actual consequential effects, explicit review and pending independent-review obligations still require an independent Reviewer. Parent may be the only implementer plus a read-only Reviewer. Only then load Handoff, Reviewer, Handoff schema and Review schema. Never skip required review or verification. Tests are not source review. Reuse evidence only for the same unchanged inputs, commands and environment.
Authority
Use host permissions and exact scope, not a second Qing approval system. on-request uses the host; never means no new permission prompt, not unrestricted access. Unknown/denied access stops affected work; no forged grants, security changes or backend bypass. Read safety-gates.md for consequential effects. Preserve unrelated work. Report actual artifacts, tests, limits, executionOwner and model substitutions, never a plan/mock as completion.
What ships with it
56 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.
- agents/openai.yaml 313 B
- references/codex-exec.md 4.1 KB
- references/execution-modes.md 1.5 KB
- references/handoff-protocol.md 1.8 KB
- references/orchestrator-spec.md 3.2 KB
- references/reviewer-rules.md 1.1 KB
- references/safety-gates.md 3.6 KB
- runtime/config/relay.gpt6.json 9.9 KB
- runtime/config/relay.user.json 858 B
- runtime/dist/src/classifier.js 2.0 KB runs code
- runtime/dist/src/cli.js 36 KB runs code
- runtime/dist/src/codex-model-catalog.js 5.0 KB runs code
- runtime/dist/src/codex-runtime.js 12 KB runs code
- runtime/dist/src/codex-usage.js 2.2 KB runs code
- runtime/dist/src/config.js 16 KB runs code
- runtime/dist/src/delegation-benefit.js 2.4 KB runs code
- runtime/dist/src/execution-mode-router.js 6.2 KB runs code
- runtime/dist/src/execution-plan.js 1.0 KB runs code
- runtime/dist/src/executors/codex-exec-executor.js 25 KB runs code
- runtime/dist/src/executors/dry-run-executor.js 848 B runs code
- runtime/dist/src/executors/executor.js 11 B runs code
- runtime/dist/src/executors/mock-executor.js 1.3 KB runs code
- runtime/dist/src/git-audit.js 12 KB runs code
- runtime/dist/src/model-health.js 17 KB runs code
- runtime/dist/src/model-router.js 15 KB runs code
- runtime/dist/src/model-scheduler.js 3.4 KB runs code
- runtime/dist/src/native-permissions.js 2.1 KB runs code
- runtime/dist/src/orchestration-policy.js 12 KB runs code
- runtime/dist/src/output-efficiency.js 2.0 KB runs code
- runtime/dist/src/planner.js 13 KB runs code
- runtime/dist/src/process-runner.js 10 KB runs code
- runtime/dist/src/protected-inputs.js 1.4 KB runs code
- runtime/dist/src/relay-criterion-collector.js 3.9 KB runs code
- runtime/dist/src/relay.js 31 KB runs code
- runtime/dist/src/reviewer.js 5.4 KB runs code
- runtime/dist/src/run-store.js 28 KB runs code
- runtime/dist/src/safety-gate.js 6.2 KB runs code
- runtime/dist/src/sandbox-preflight.js 4.4 KB runs code
- runtime/dist/src/single-owner-controller.js 5.5 KB runs code
- runtime/dist/src/single-owner-policy.js 801 B runs code
- runtime/dist/src/task-analyzer.js 2.9 KB runs code
- runtime/dist/src/task-router.js 17 KB runs code
- runtime/dist/src/types.js 11 B runs code
- runtime/dist/src/validation.js 24 KB runs code
- runtime/dist/src/workspace-lease.js 2.0 KB runs code
- runtime/dist/src/workspace.js 1.5 KB runs code
- runtime/package.json 2.0 KB
- runtime/schemas/criterion-evidence.schema.json 932 B
- runtime/schemas/executor-result.schema.json 2.3 KB
- runtime/schemas/handoff.schema.json 6.8 KB
- runtime/schemas/model-health.schema.json 438 B
- runtime/schemas/model-route.schema.json 16 KB
- runtime/schemas/planner-output.schema.json 4.5 KB
- runtime/schemas/review.schema.json 2.6 KB
- runtime/schemas/test-evidence.schema.json 1.4 KB
- scripts/qing.ps1 1.3 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.
- 1mo ago Changed · -4 lines · -10 tokens per session 42b2fbf9f7c9
- 2mo ago Changed · -6 lines · -47 tokens per session d7e8281535c7
- 2mo ago First seen · 33 lines · 83 tokens per session scan A b4293cb23629
qing-agent-orchestrator-full is a skill published in the GitHub repository qingshihuan/qing-agent-orchestrator (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 523 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
qing-agent-orchestrator-full compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qing-agent-orchestrator-fullqingshihuan/qing-agent-orchestrator | Skill | 2 | 1mo ago | MIT | A | 26 | Codex |
| subagentsWaishnav/devspace | Skill | 5.4k | 6d ago | MIT | A | 44 | Claude Code, Codex |
| workflowsWaishnav/devspace | Skill | 5.4k | 6d ago | MIT | A | 34 | Claude Code, Codex |
| codex-auth-setupndycode/codex-multi-auth | Skill | 565 | 3d ago | MIT | A | 32 | Claude Code, Codex |
| examplendycode/codex-multi-auth | Skill | 565 | 3d ago | MIT | A | 10 | Claude Code, Codex |
| kanban-orchestratorforcewake/hermes-conductor | Skill | 82 | 2mo ago | MIT | A | 21 | Claude Code, Codex |
| dynamic-workflowsccbud/CCBuddy | Skill | 8 | 24d ago | Apache-2.0 | A | 100 | Claude Code |