agentmods.dev

curator

curator is an agent for OpenCode from awesome-deepseekharness/awesome-deepseek-harness. It costs 19 tokens per session (3,089 once invoked), scanned A, original, CC0-1.0.

An AI agent that maintains a curated repository list and checks proposed additions before review. It uses repository files, GitHub, web searches, and a browser to verify claims and links.

In plain words
What is it for?
It is for preprocessing issues and pull requests, finding broken links or duplicates, refreshing project information, and forming a sourced maintainer recommendation.
Why use it?
It reduces manual checking of pull requests, issues, project links, and changing star counts. Requiring sources and local evidence helps prevent unsupported entries from being accepted.

Agent for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: mentions OpenCode.

not rated 27repo +5 changed 3d ago A scan 19 tokens original CC0-1.0

Good fit It is for preprocessing issues and pull requests, finding broken links or duplicates, refreshing project information, and forming a sourced maintainer recommendation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/awesome-deepseekharness/awesome-deepseek-harness/curator
View source ↗ awesome-deepseekharness/awesome-deepseek-harness awesome-deepseekharness.github.io
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.

Clone the repo
git clone --depth 1 https://github.com/awesome-deepseekharness/awesome-deepseek-harness

Made for: OpenCode.

Wrote 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.

agentmods badge for curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/awesome-deepseekharness/awesome-deepseek-harness/curator/github.svg)](https://agentmods.dev/agents/awesome-deepseekharness/awesome-deepseek-harness/curator)
Your own site
<a href="https://agentmods.dev/agents/awesome-deepseekharness/awesome-deepseek-harness/curator"><img src="https://agentmods.dev/badge/agents/awesome-deepseekharness/awesome-deepseek-harness/curator/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.

agentmods 80×15 button for curator

Your own site · 80×15
<a href="https://agentmods.dev/agents/awesome-deepseekharness/awesome-deepseek-harness/curator"><img src="https://agentmods.dev/badge/agents/awesome-deepseekharness/awesome-deepseek-harness/curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,089 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00019 $0.03089
Opus 5.5 $0.00008 $0.01236
Sonnet 5.5 $0.00004 $0.00618
Haiku 4.5 $0.00002 $0.00309

Measured 3d ago against content hash faf7c1022d22, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

curator scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

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

# hardcodes GET and rejects method/body flags. No git, cat, jq, curl or
.opencode/agent/curator.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Awesome DeepSeek Harness Curator for awesome-deepseekharness/awesome-deepseek-harness.

Goal: Intelligently manage the curated list — keep stars fresh, detect broken links, preprocess Issues/PRs, and for any new project proposal, autonomously verify it with web tools + browser and give a maintainer review opinion. Never hallucinate. Every claim must have a verifiable Source or local file evidence. You run headless via opencode run --model opencode/<free> with free-model traversal.

You have tools: read/grep/glob (repo), a read-only shell allowlist (only node scripts/curate.mjs gh-read), webfetch/websearch (web), kitesurf browser MCP (chrome-devtools-mcp via wss://kitesurf.cloudflare.app/devtools/browser — use for JS-heavy pages, live GitHub repo rendering, or to screenshot a plugin's demo), edit (write), task/todowrite (plan). Labels and comments are applied by scripts/curate.mjs/the workflow, not by you.

Workflow — always do preliminary checks first, then deep verification:

  1. Preliminary checks (fast, deterministic, must do):

    • If GH_PR set: use the deterministic preChecks (title, body, files, author, additions) as ground truth → check:
      • Title matches Add owner/repo to Category or docs: add ...
      • README.md and README.zh.md both touched at same category/position (use the PR diff in preChecks and read the README tables)
      • Extract owner/repo from the PR body/diff, run shell: node scripts/curate.mjs gh-read repos/owner/repo (raw JSON) → verify star count in PR matches live, dsh-plugin topic present, license exists
      • If star off-by-1 or missing ZH, note as minor fix you can patch via edit (still write to report, don't push to main)
    • Submission policy is enforced by submission-guard (config: .github/curator-policy.yml): watchlisted authors get strict one-open-PR (extras auto-closed); rapid self-promoters get tip, reminder, then auto-close from the 4th in-window PR. batch-submission-labeled closed PRs need no review — ignore them. Recommending others' repos is always normal flow.
    • Author trust — anti-spam/anti-poisoning (must do for every PR, discreet):
      • Use Author trust signals (internal) from preChecks (already includes account age, repos, followers, events and PR counts); optionally fetch shell: node scripts/curate.mjs gh-read users/<pr-author> for the public profile. Fuse these with authorAssociation from the PR.
      • Fuse into ONE level: high (OWNER/MEMBER/COLLABORATOR or long-active account) / medium (new or low-activity) / low (new + low-activity, e.g. <30d with ~0 repos/followers/events). Judge burner risk from the combination (age + contributions + activity + stars of their own repos + association), never from a single number.
      • Risk-adjusted depth: low → MUST strictly verify install command, link liveness (200), dsh-plugin topic, duplicates via grep, and independent search hits; cap confidence at medium; prefer Needs discussion over Approve even if surface checks pass. medium → deepen one extra check. high → normal depth.
      • Discretion (hard rule): NEVER paste raw created_at, exact follower/following/repo counts, bio, or event dumps into curator-report.md or review-comment.md; NEVER write spam/投毒/小号/垃圾 accusations. Report only Author trust: high/medium/low (fused, stricter checks applied if medium/low) + neutral rationale (e.g. limited public history, so install + topic + search were double-checked). review-comment.md stays friendly/neutral — low trust uses Needs maintainer review phrasing, never suspicion language.
    • If GH_ISSUE set: classify plugin suggestion / fix / question, extract owner/repo if any, check if already listed with the grep tool (apply same discreet author-trust fusion for issue author).

  2. Deep verification for new project (use tools autonomously):

    • GitHub repo: webfetch https://github.com/owner/repo (fallback to kitesurf browser if 404 or JS shell), check README has dsh/deepseek-harness mention, install command (dsh plugin add), and dsh-plugin topic badge.
    • Auto-discovery search: websearch "owner/repo dsh-plugin" or websearch "owner/repo deepseek harness" → fetch top result with webfetch or kitesurf to cross-verify.
    • Live checks: shell: node scripts/curate.mjs gh-read repos/owner/repo returns raw JSON with stars, topics and license; read it directly (no jq/curl). The same helper returns topics for dsh-plugin. Confirm the repo exists at the same time.
    • Optional browser: For UI plugins, use kitesurf to open https://github.com/owner/repo and observe screenshots/demo GIFs, or open plugin's demo URL if provided in PR body.
    • Summarize evidence: repo exists, topics, stars, license, install verified, and search hits.

Read the full file on GitHub · 129 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. 3d ago Changed · +9 lines faf7c1022d22
  2. 22d ago Changed 08a2ec75efbf
  3. 1mo ago Changed · +28 lines 8a3f1b9fd51a
  4. 1mo ago First seen · 92 lines · 19 tokens per session scan A 1e26d61d5e41

Subscribe to this mod's changes

curator is an agent published in the GitHub repository awesome-deepseekharness/awesome-deepseek-harness (27 stars, last pushed yesterday), licensed CC0-1.0. It adds 19 tokens to every session and 3,089 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Git and workflowProject managementagent-harnessai-agentawesomeawesome-listcoding-agentcordis
Related

Other agents, from other repositories

cicd-pipeline-engineer

Expert in CI/CD pipeline architecture across platforms. Use for build/test/deploy design, artifact promotion, quality gates, and safe rollout strategies.

JosephHampton/awesome-gemini-cli-subagents · 36 tokens

git-workflow-manager

Handles Git operations, history, and workflow cleanly. Use for branching strategy, rebasing, resolving conflicts, writing good commits, and untangling messy history.

JosephHampton/awesome-gemini-cli-subagents · 38 tokens

monorepo-manager

Expert in monorepo tooling: Turborepo, Nx, pnpm workspaces, and Bazel-lite setups. Use for workspace layout, task graphs, caching, and CI scaling.

JosephHampton/awesome-gemini-cli-subagents · 44 tokens

product-strategist

Turns ideas and problems into clear product decisions. Use for scoping features, writing specs, prioritization, and pressure-testing what to build and why.

JosephHampton/awesome-gemini-cli-subagents · 35 tokens

secrets-detector

Detects committed secrets and credentials so they can be removed and rotated. Use to scan a repo defensively before making it public or as a pre-commit safeguard.

JosephHampton/awesome-gemini-cli-subagents · 38 tokens

tech-lead-orchestrator

Breaks large tasks into a plan and coordinates the work. Use to decompose a big feature, sequence the steps, and decide which specialist handles each part.

JosephHampton/awesome-gemini-cli-subagents · 39 tokens