Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add CanXiangCC/aminer-open-skill/plugin install aminer-deep-searchWrote 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/canxiangcc/aminer-open-skill/aminer-deep-search)<a href="https://agentmods.dev/commands/canxiangcc/aminer-open-skill/aminer-deep-search"><img src="https://agentmods.dev/badge/commands/canxiangcc/aminer-open-skill/aminer-deep-search/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/canxiangcc/aminer-open-skill/aminer-deep-search"><img src="https://agentmods.dev/badge/commands/canxiangcc/aminer-open-skill/aminer-deep-search.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 | $0.00015 | $0.00923 |
| Opus 5 | $0.00008 | $0.00462 |
| Sonnet 5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
aminer-deep-search 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aminer-deep-search — 100% identical, 26 lines differ
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aminer-deep-search - AMiner Deep Search
User invoked the AMiner deep paper collection skill with the following arguments:
$ARGUMENTS
Your task
Follow ${CLAUDE_PLUGIN_ROOT}/SKILL.md. You are the controller: run the tool scripts, read their JSON output, judge relevance yourself, and iterate. There is no external LLM mode and nothing to configure beyond AMINER_API_KEY.
Gate check first: this command is only for large-scale collection — 50+ candidate papers, survey bibliography construction, or citation snowballing. If the user actually wants a single lookup, a survey-style answer, or a small reading list, say so and point them to aminer-free-academic / aminer-academic-search instead of running the loop.
1. Parse $ARGUMENTS
topic: required research topic. Preserve the user's wording. If absent or too vague, ask for a concrete topic.target-size: optional final paper target, default 400.max-rounds: optional round budget, default 12.- Structured constraints (all optional):
year-from/year-to,venues,authors,orgs,languages,exclude(exclusion terms),sort-goal(latest|impact|classic+latest). Also extract any of these stated in free text.
2. Pre-flight
[ -z "${AMINER_API_KEY:-}" ] && echo "AMINER_API_KEY missing" || echo "AMINER_API_KEY exists"
If missing, stop and tell the user to set AMINER_API_KEY. Never print the key. The scripts are pure stdlib — no dependency installation is needed.
Record the hard constraints so every add enforces them:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/paper_set.py" init --topic "..." \
--year-from 2020 --year-to 2025 --require-fields year
3. Run the round protocol
Execute the Round Protocol from ${CLAUDE_PLUGIN_ROOT}/SKILL.md:
- Round 0: derive 4–8 seed queries, pick the ranking strategy from
sort-goal(forclassic+latest, run each query under both--order n_citationand--order year), estimate cost; confirm with the user if the estimate is ≥¥5. - Each round (max
max-rounds): search viapython3 "${CLAUDE_PLUGIN_ROOT}/scripts/aminer_api.py" search --query "..." [--author ... --org ... --venue ... --year-from ... --year-to ...] --order n_citation(useqa-search-proonly for constraintssearchcannot express: languages, exclusion terms, citation ranges), filter results for relevance yourself, add the kept items viapython3 "${CLAUDE_PLUGIN_ROOT}/scripts/paper_set.py" add --source "search:<query>", snowball withreferences --ids ...on ≤5 strong unexpanded seeds, checkstats, and log the round withlog-round --queries ... --added N --rejected R. - Stop when
target-sizeis reached, results are exhausted, or 2 consecutive rounds add <5 papers.
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.
- 7d ago Changed · +10 lines · +5 tokens per session e72fda4a8bdd
- 11d ago First seen · 52 lines · 10 tokens per session scan A d19fb74efaee
aminer-deep-search is a command published in the GitHub repository CanXiangCC/aminer-open-skill (60 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 923 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.