Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SunflowersLwtech/sunkitnpx agentmods add commands/sunflowerslwtech/sunkit/searchpo-full-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/commands/sunflowerslwtech/sunkit/searchpo-full-flow)<a href="https://agentmods.dev/commands/sunflowerslwtech/sunkit/searchpo-full-flow"><img src="https://agentmods.dev/badge/commands/sunflowerslwtech/sunkit/searchpo-full-flow/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/commands/sunflowerslwtech/sunkit/searchpo-full-flow"><img src="https://agentmods.dev/badge/commands/sunflowerslwtech/sunkit/searchpo-full-flow.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 | $0.00022 | $0.01691 |
| Opus 5.5 | $0.00009 | $0.00676 |
| Sonnet 5.5 | $0.00004 | $0.00338 |
| Haiku 4.5 | $0.00002 | $0.00169 |
Grade A, and why
searchpo-full-flow 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 2mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Searchpo Full Flow
Run the Searchpo main/research/impl flow end to end for an operator-supplied topic or link.
Use the searchpo-main-agent skill. In Claude/Codex agent-team mode, the main agent must assign source research/cross-check to searchpo-research-agent, provider/render/audit/upload execution to searchpo-impl-agent, and keep the final release decision itself.
For Codex, selecting this slash command or skill is not enough to prove a real team run. If the host exposes subagent tools, use this exact team shape before running provider/live commands:
Use the searchpo-main-agent as lead. Do not run research and implementation in parallel. First spawn or assign only searchpo-research-agent for AnySearch-first source discovery/extraction, GitHub API/README evidence, FactBank/TopicBrief, cross-check tasks, and only supporting DeepWiki repo context when useful. Wait until the main agent verifies cross_check_review.status == pass and research_sufficient == true, then spawn or assign searchpo-impl-agent for provider, render, audit, and Douyin tasks. The main agent must not run implementation commands itself; it verifies artifacts and makes the final release decision.
If subagent tools are not available, say so before execution, follow the same ownership split manually, and report the result as manual fallback.
When spawned teammates are available, use the phased runtime so owner labels line up with actual command boundaries:
python3 agent_harness/run_agent_loop.py --topic "topic" --mode provider --stop-after research_enrichment --delegation-mode spawned_subagents --delegation-agent searchpo-research-agent --delegation-proof "<host-subagent-id>"
python3 agent_harness/run_agent_loop.py "<run_dir>" --mode provider --resume-from 4 --stop-after main_task_plan --delegation-mode spawned_subagents --delegation-agent searchpo-main-agent --delegation-proof "<host-subagent-id>"
python3 agent_harness/run_agent_loop.py "<run_dir>" --mode provider --resume-from 5 --delegation-mode spawned_subagents --delegation-agent searchpo-impl-agent --delegation-proof "<host-subagent-id>"
For synchronous shell runs, keep SEARCHPO_DELEGATION_MODE=single_harness or set SEARCHPO_DELEGATION_MODE=manual_fallback; never report those as spawned subagents.
Raw slash-command arguments:
$ARGUMENTS
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.
- 2mo ago First seen · 117 lines · 22 tokens per session scan A 3ffa4b61911a
searchpo-full-flow is a command published in the GitHub repository SunflowersLwtech/sunkit (13 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 1,691 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 2026-08-30.
Other commands, from other repositories
component
Command "component" from TidyFactor/Styler, covering command: component — create or redesign a single component, when to use, dispatch steps and do not load.
page
Command "page" from TidyFactor/Styler, covering command: page — build a new production page, when to use, dispatch steps and do not load.
section
Command "section" from TidyFactor/Styler, covering command: section — create or redesign a page section, when to use, dispatch steps and do not load.
redesign
Command "redesign" from TidyFactor/Styler, covering command: redesign — redesign an existing production page, when to use, dispatch steps and do not load.
rtl
The bar this command holds work to is already stated once, in SKILL.md's non-negotiable constraint 5 and in rtl-css-engineering.md itself — not repeated here.
motion
Motion work is applied within whatever component/section/page workflow is already running. If motion is the entire ask with nothing else changing, this command's steps above are sufficient on their own.