dsh-zotero AGENTS.md

Repository instructions for dsh-zotero, a plugin connected to the deepseek-harness project and its local development workspace.

In plain words
What is it for?
Finding related documentation, checking harness contracts, installing dependencies, and creating commits that follow the project's format.
Why use it?
They identify the authoritative source code and set commit and development rules, reducing the risk of changing the plugin without understanding its underlying system.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/vncntvx/dsh-zotero/agents-md
Clone the repo
git clone --depth 1 https://github.com/Vncntvx/dsh-zotero

Made for: Codex, OpenCode.

Per session 3,308 This file is loaded in full into every session.
When invoked 3,308 The same file — it is already loaded in full.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03308 $0.03308
Opus 5 $0.01654 $0.01654
Sonnet 5 $0.00662 $0.00662
Haiku 4.5 $0.00331 $0.00331

Measured yesterday against content hash 4efb75859aa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

dsh-zotero AGENTS.md scanned grade B with 2 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 yesterday.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 "$DSH_HOME/.credentials.yaml" "$DSH_HOME/settings.yaml"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -w '%{http_code}' -o /dev/null http://127.0.0.1:3307 # 200
AGENTS.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Workspace and source of truth

  • You work in . This repo is a standalone sibling to ../deepseek-harness. You keep it beside the harness for local dev. Treat this as temp local layout, hard-coded for your machine.
  • You find the dsh source in ../deepseek-harness. Read ../deepseek-harness/docs/AGENTS.md, ../deepseek-harness/docs/architecture.md, ../deepseek-harness/docs/user/develop/, ../deepseek-harness/docs/subsystems/, ../deepseek-harness/docs/cookbook/, and ../deepseek-harness/packages/*/README.md when you touch harness contracts.
  • You touch slots, services, the web shell, the client-module graph, or Typert, so you check harness source first. Harness source outranks this file.

Git commit conventions

Follow Conventional Commits: <type>(<scope>): <subject>, types lowercase (feat, fix, refactor, docs, test, chore, perf, style, build, ci, revert), subject in imperative mood, header under 72 chars. Optionally place an emoji matching the type right after the colon, before the subject. Body: blank line, bullet points only, each item wraps at 72, what and why.

Commands

npm install                  # sibling at ../deepseek-harness; add --no-workspaces only for a nested copy
npm run typecheck            # tsc --noEmit for the node, test, and client projects
npm test                     # vitest unit tests against the mock Zotero server
npm run test:coverage        # coverage gate on src/ (97 stmts / 95 branches / 98 funcs / 97 lines); pure re-export and types-only modules excluded, see vitest.config.ts
npm run build                # tsc emits the node half into lib/; esbuild emits the browser half lib/client.js (with a loader-handoff self-check)
npm run build:client         # rebuild the browser half only
npm run dev                  # tsc --watch
npm run dev:client           # esbuild --watch for the browser half
npm run format               # prettier --write across the repo
npm run format:check         # verify formatting; run before committing
npm run test:integration     # live Zotero at 127.0.0.1:23119; skipped unless ZOTERO_INTEGRATION=1

Read the full file on GitHub · 126 lines

Changes

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.

  1. yesterday First seen · 126 lines · 3,308 tokens per session scan B 4efb75859aa8

Subscribe to this mod's changes

dsh-zotero AGENTS.md is an instructions file published in the GitHub repository Vncntvx/dsh-zotero (10 stars, last pushed 2d ago), licensed MIT. It adds 3,308 tokens to every session, about $0.0165 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.