DeerFlow is an open-source super-agent harness that coordinates sub-agents, memory, tools, sandboxes, and extensible skills to handle research, coding, and content-creation tasks that may run for minutes or hours. It is intended for long-running, multi-step work performed by AI agents. The catalogue entries are skills, agents, and instructions that support its workflows.
Borrowing it
Nothing to install: this file belongs to bytedance/deer-flow. 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/bytedance/deer-flow/main/.agent/skills/deerflow-maintainer-orchestrator/SKILL.mdgit clone --depth 1 https://github.com/bytedance/deer-flowWrote 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/bytedance/deer-flow/deerflow-maintainer-orchestrator)<a href="https://agentmods.dev/skills/bytedance/deer-flow/deerflow-maintainer-orchestrator"><img src="https://agentmods.dev/badge/skills/bytedance/deer-flow/deerflow-maintainer-orchestrator/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/bytedance/deer-flow/deerflow-maintainer-orchestrator"><img src="https://agentmods.dev/badge/skills/bytedance/deer-flow/deerflow-maintainer-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 12 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 204 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00088 | $0.04593 |
| Opus 5 | $0.00044 | $0.02296 |
| Sonnet 5 | $0.00018 | $0.00919 |
| Haiku 4.5 | $0.00009 | $0.00459 |
Grade A, and why
deerflow-maintainer-orchestrator 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 10d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeerFlow Maintainer Orchestrator
Core Rule
This is a comment-plane skill: resolve GitHub scope, inspect evidence, and prepare or post DeerFlow issue comments and PR review comments. Keep the work comment-scoped; do not turn it into coding, branch management, release work, artifact closure, or other maintainer operations.
When the maintainer asks to process, handle, comment on, or review a bounded set of issues or PRs, proceed without asking follow-up questions. Treat that request as authorization for one public issue comment per selected non-skipped issue and one PR review comment per selected PR with high-confidence findings. If a PR has no high-confidence findings, do not post a public comment; report that result to the maintainer only. If the maintainer explicitly asks for analysis only, return comment-ready drafts without posting.
The maintainer's normal interaction should be: provide scope; receive posted comment URLs, PR review URLs, clean results, skipped items, failures, or drafts. Do not offload technical analysis to the maintainer. Make the best evidence-backed recommendation in the comment itself: describe the risk, impact, likely fix, and validation path. Ask the reporter or PR author for missing evidence only when the artifact lacks enough data to diagnose.
Output only the maintainer run result or comment draft. Do not announce the skill name, mode, or that no code was edited unless the user asks for process details.
Match the dominant language of the issue or PR unless the maintainer asks for another language. Chinese issue or PR text gets Chinese output; English issue or PR text gets English output. For mixed artifacts, use the body language, not logs or code.
Artifact Resolution
Use GitHub tooling to resolve artifact type and scope. Do not ask the maintainer to clarify when gh or GitHub API can determine the answer.
- Default repository is
bytedance/deer-flowunless a URL or explicit repo says otherwise. - For URLs, route
/issues/<number>to Issue Flow and/pull/<number>to PR Review Flow. - For typed numbers, use the typed command:
- Issue:
gh issue view <number> --repo <repo> --json number,title,url,state,body,labels,author,comments - PR:
gh pr view <number> --repo <repo> --json number,title,url,state,body,author,files,comments,reviews,statusCheckRollup,baseRefName,headRefName
- Issue:
- Normalize multiple explicit references such as
#123,# 123, and bare123into a number list, preserving order and de-duplicating exact repeats. - For untyped numbers, try
gh pr view <number> --repo <repo> --json number,urlfirst. If it fails, usegh issue view <number> --repo <repo> --json number,url. Do not ask which type it is. - For issue batches, use
gh issue list, not the mixed GitHub issues endpoint. For PR batches, usegh pr list. - Respect maintainer-provided count or time window. There is no hard five-item cap. If the scope is broad and underspecified, choose a practical recent slice, state the slice used, prioritize newest and highest-risk items, and report any unprocessed remainder.
- For "recent/latest" wording without a count, use a small default recent slice. For "recent hours" wording without a number, use six hours. Do not ask.
- Use
gh apiwhengh issue/pr view/listlacks required fields such as timeline events, review threads, or precise search filters. - Use GitHub search only as a fallback for natural-language filters that cannot be represented by view/list/API calls. Do not use web search for artifact routing unless GitHub tooling is unavailable.
- When an issue has more than one candidate resolving PR, gather them all before reviewing: the issue's linked/Development PRs, closing keywords (
Closes/Fixes #<issue>) found viagh apitimeline cross-reference events, and PRs that mention the issue. Route them into Competing PR Comparison. - If no artifact type, number, URL, count, time window, or searchable GitHub scope can be resolved, stop with a compact "scope unresolved" report. Do not ask a follow-up question.
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.
- 10d ago First seen · 294 lines · 88 tokens per session scan A bdd3e985cf00
deerflow-maintainer-orchestrator is a skill published in the GitHub repository bytedance/deer-flow (82,196 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 4,593 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
github-deep-research
Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams.…
code-review
Comprehensive code review for security, performance, and best practices.
contribute-to-eliza
Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…
review-pr
Review a pull request (GitHub) or merge request (GitLab) and provide detailed feedback.
05-review
Review a diff read-only on three axes, code, behavior versus the plan, and relevancy, into one verdict report. Use before shipping a change. Not for fixing findings or auditing a codebase.
pr-gates
This skill should be used when the user asks to "open a PR", "prepare for review", "address review comments", "run gates", or "verify before pushing" in this repository. Enforces preflight/gate workflow, migration safety, and review-evidence closure.