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/Chip-G0202/PaperEchonpx agentmods add skills/chip-g0202/paperecho/paperecho-zotero-webWrote 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/chip-g0202/paperecho/paperecho-zotero-web)<a href="https://agentmods.dev/skills/chip-g0202/paperecho/paperecho-zotero-web"><img src="https://agentmods.dev/badge/skills/chip-g0202/paperecho/paperecho-zotero-web/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/chip-g0202/paperecho/paperecho-zotero-web"><img src="https://agentmods.dev/badge/skills/chip-g0202/paperecho/paperecho-zotero-web.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 16 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00060 | $0.01924 |
| Opus 5.5 | $0.00024 | $0.00770 |
| Sonnet 5.5 | $0.00012 | $0.00385 |
| Haiku 4.5 | $0.00006 | $0.00192 |
Grade A, and why
paperecho-zotero-web 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 2d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PaperEcho - Zotero Web
First-run is GUI-only; Headless uses the saved config and original preflight without a wizard completion flag. Setup never validates keys against real providers; see shared workspace rules in configuration.
The packaged PaperEcho-headless.cmd --check --mode web entry reuses Shared Runner and the same Stage0 core. See configuration for data-root setup, embedded runtime/fuse requirements and Windows-only packaging acceptance; packaging tests use no real provider credentials.
Deployment paths reuse the shared runtime_config.mjs Portable/Installed/Dev contract, independently of Web backend selection. See configuration. Do not add adapter root discovery or implicitly migrate data.
No-desktop Zotero Web path for PaperEcho. Keep work narrow: prefer Stage2-only benchmark and targeted tests, and run the full workflow only for final end-to-end acceptance.
Execution Intent Routing
The optional Control Center is a localhost interaction UI, distinct from the Zotero Web API path. It does not launch this path or call Zotero. Stage1 consumes canonical feedback with legacy XLSX fallback; production still follows the launcher below.
- Production intent such as “运行”, “跑一次”, “完整流程”, “文献追踪”, “检查配置并启动”, or “配置完成，继续” must use only
node skills/paperecho-zotero-web/scripts/run.mjs. Pass--config config/paperecho.config.jsonwhen using unified configuration. With sufficient parameters, invoke--run; when only safe configuration inspection is possible, invoke--check. - Development intent such as modifying, fixing, refactoring, auditing code, or updating tests must not invoke the production launcher. Use mocks and targeted validation.
- Explanation intent must only explain or invoke
--check; never invoke--run. - A reply of “继续” reruns the same launcher with the same
--config, reloads the file, and performs a fresh preflight. Inspect onlycommonplusweb; do not reuse readiness, wait in the background, start Desktop, or switch to Desktop/Local. - Never ask the user to paste
ZOTERO_API_KEYor another secret into chat. Loading this Skill alone causes no production side effect, and production execution must not modify code or create a Git commit.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +6 lines 9502094b532e
- 1mo ago Changed · +2 lines 263958799eda
- 2mo ago First seen · 112 lines · 60 tokens per session scan A 7e2d4ac1157f
paperecho-zotero-web is a skill published in the GitHub repository Chip-G0202/PaperEcho (76 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 1,924 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 2026-08-30.
paperecho-zotero-web compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paperecho-zotero-webChip-G0202/PaperEcho | Skill | 76 | 3d ago | MIT | A | 60 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |