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 lfyxhappy/lfcode --skill deep-researchgit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/deep-research)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/deep-research"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/deep-research/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/lfyxhappy/lfcode/deep-research"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/deep-research.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 | $0.00056 | $0.00367 |
| Opus 5.5 | $0.00022 | $0.00147 |
| Sonnet 5.5 | $0.00011 | $0.00073 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
deep-research 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.
What it actually says
Deep Research
Run this as a background research coordination task. Use local project files only to clarify the user's context; the primary evidence must come from current online sources and the project's research cache.
Method
- Select quick for a narrow factual question, standard for a comparison or decision, and deep for a broad, high-stakes, or time-sensitive investigation.
- Split standard or deep research into at most three independent lines: primary evidence, complementary evidence, and a contrarian or verification pass. The coordinator must issue the actor.spawn calls before replying with any plan, then use actor.wait and synthesize the returned evidence. Delegate only to the read-only researcher Agent in background mode. Do not let delegated researchers dispatch further Agents.
- Prefer official, primary, institutional, and recent sources. Reuse cached evidence when still relevant, fetch authoritative pages when needed, and record URLs for every material claim.
- Cross-check important claims, numbers, dates, quotations, and causal conclusions. Treat a source disagreement as a finding, not an error to hide.
- Return a concise report with scope and cutoff time, findings labeled as facts or inferences, source citations, confidence/caveats, and unresolved questions.
Boundaries
- Do not claim to have browsed, verified, or cited material that is unavailable.
- Do not use local code or documents as a substitute for required external evidence.
- Do not edit project files, access restricted sources, collect sensitive personal data, or publish results externally.
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 First seen · 23 lines · 56 tokens per session scan A e88c48b44c30
deep-research is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 26d ago), licensed MIT. It adds 56 tokens to every session and 367 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
PR babysit (watch & drive to green)
Watch a pull request and delegate fixes until CI is green and reviews are addressed. Requires the GitHub MCP server or gh.
Review changes (multi-agent)
Delegate read-only reviewers over the local changes/branch and consolidate findings.