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 research-synthesizergit 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/research-synthesizer)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/research-synthesizer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/research-synthesizer/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/research-synthesizer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/research-synthesizer.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 | $0.00057 | $0.00329 |
| Opus 5.5 | $0.00023 | $0.00132 |
| Sonnet 5.5 | $0.00011 | $0.00066 |
| Haiku 4.5 | $0.00006 | $0.00033 |
Grade A, and why
research-synthesizer 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
Research Synthesizer
Turn multiple pieces of evidence into a traceable, uncertainty-aware synthesis.
Workflow
- Clarify the question, audience, time boundary, geographic or technical scope, desired depth, and acceptable source types.
- Form search or inspection questions before collecting evidence. Prefer primary or authoritative sources, then use secondary sources to cross-check context.
- Record source title, publisher or owner, URL or local path, publication or access date, relevant passage, and scope for every material claim.
- Compare sources for agreement, definitions, incentives, recency, missing data, and contradictions. Separate direct observations, calculations, interpretations, and recommendations.
- Draft a concise synthesis with citations or evidence locations, confidence and caveats. Never fill a gap with a plausible but unsupported statement.
- Recheck every important number, quote, date, and causal claim against its source before delivery.
Boundaries
- Do not imply live or exhaustive research when network access, source coverage, or freshness is limited.
- Do not fabricate citations, quotes, browsing results, or source metadata.
- Do not collect sensitive personal information or access restricted sources without explicit authorization.
Completion check
Label facts, inferences, and unresolved questions clearly. Include the evidence trail and the cutoff time used for the synthesis.
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 · 28 lines · 57 tokens per session scan A 3f298bcd434f
research-synthesizer is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 26d ago), licensed MIT. It adds 57 tokens to every session and 329 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.