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.
git clone --depth 1 https://github.com/CanXiangCC/aminer-open-skillWrote 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/deep-research)<a href="https://agentmods.dev/commands/canxiangcc/aminer-open-skill/deep-research"><img src="https://agentmods.dev/badge/commands/canxiangcc/aminer-open-skill/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/commands/canxiangcc/aminer-open-skill/deep-research"><img src="https://agentmods.dev/badge/commands/canxiangcc/aminer-open-skill/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 | $0.00015 | $0.01247 |
| Opus 5 | $0.00008 | $0.00624 |
| Sonnet 5 | $0.00003 | $0.00249 |
| Haiku 4.5 | $0.00002 | $0.00125 |
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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/deep-research - Deep Research
User invoked the deep-research skill with the following arguments:
$ARGUMENTS
Your task
Follow ${CLAUDE_SKILL_DIR}/SKILL.md. You are the researcher: scout the question, induce the outline from what retrieval returns, retrieve per section, keep every source in an evidence ledger, and write a cited report where each claim points back to a retrieved source. No claim reaches the report without a ledger source.
Use this command for tasks that need a sourced report — literature review, research landscape, entity investigation, trend comparison, or industry / market survey — not for a single lookup or a bare bibliography.
1. Parse $ARGUMENTS
topic: required research topic. Preserve the user's wording. If absent or too vague, ask for a concrete topic (at most two questions, and only when different answers would change the scope).genre: optional,academic(default — literature reviews, landscapes, investigations) orindustry(industry / market surveys: "行业调研", "市场格局", "竞争格局").
2. Pre-flight
Check the key without printing it:
[ -z "${AMINER_API_KEY:-}" ] && echo "AMINER_API_KEY missing" || echo "AMINER_API_KEY exists"
If missing, stop and ask the user to set AMINER_API_KEY (console: https://open.aminer.cn/open/board?tab=control). Never print the key. The scripts are pure stdlib — no dependency installation is needed except matplotlib for figure rendering (see requirements.txt).
Set the workspace once — the skill owns no ledger location, the path is the host's choice. The default (overridable via $DR_WORKDIR) is a per-run directory under the current project: outputs/<topic-slug>-<YYYYMMDD-HHMM>/, resolved to an absolute path at invocation time. Derive the slug from the topic (letters / digits / CJK / hyphens, ≤40 chars); every run gets its own directory, so runs never overwrite each other:
export DR_WORKDIR="${DR_WORKDIR:-$(pwd)/outputs/<topic-slug>-$(date +%Y%m%d-%H%M)}"
export DR_LEDGER="${DR_WORKDIR}/evidence-ledger.json"
mkdir -p "$DR_WORKDIR/figures"
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.
- 9d ago First seen · 61 lines · 15 tokens per session scan A cc55e9fc4f61
deep-research is a command published in the GitHub repository CanXiangCC/aminer-open-skill (59 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,247 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.