agentmods.dev

dsh-doublecheck AGENTS.md

Repository instructions for a DeepSeek coding harness plugin called `dsh-doublecheck`. They describe its plugin packages, verification workflow, policy gates, commands, and project layout.

In plain words
What is it for?
Use them when changing the Grill, Guard, or Invariant plugin areas, their commands and tools, or the verification state and review workflow.
Why use it?
They tell an agent where each part lives and which checks govern planning, test-driven development, execution, and adversarial review.

Instructions file for CodexOpenCode

11 2d ago A scan 1,522 tokens original Apache-2.0
View the source file PerryLink/dsh-doublecheck
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/perrylink/dsh-doublecheck/agents-md
Clone the repo
git clone --depth 1 https://github.com/PerryLink/dsh-doublecheck

Made for: Codex, OpenCode.

Per session 1,522 This file is loaded in full into every session.
When invoked 1,522 The same file — it is already loaded in full.
Security scan A 0 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 $0.01522 $0.01522
Opus 5 $0.00761 $0.00761
Sonnet 5 $0.00304 $0.00304
Haiku 4.5 $0.00152 $0.00152

Measured 2d ago against content hash 46d095844be7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dsh-doublecheck AGENTS.md 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.

AGENTS.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Standalone DeepSeek Harness plugin repository (dsh-doublecheck). Development follows the dsh-plugin-guide skill and the official plugin contract; this file records repo-local decisions.

Layout

  • src/index.ts — package entry: the shared domain model and pure helpers. It is NOT a plugin; the installable plugin rows live at the ./grill and ./guard subpath exports (see cordis.patch.yml).
  • src/invariant.ts — the package-owned invariant companion; its standalone row loads via the ./invariant subpath export (reports write-path contradictions without the guard).
  • src/grill/index.ts — plugin row doublecheck-grill: bundled grill-requirements skill provider + the model-facing contract tools (doublecheck_skills, doublecheck_spec, doublecheck_report) and the v0.4 verification workflow.
  • src/guard/index.ts — plugin row doublecheck-guard: the policy gates (grill / tdd red-green / adversary review) on the tools/pre-execute and tools/post-execute waterfalls.
  • src/guard/command.ts — the /doublecheck status|report|on|off session command and the durable doublecheck/state fold.
  • src/guard/review.ts — adversary review orchestration (forked critic subagent, structured findings, honest "unavailable" degradation).
  • src/guard/gate.ts — the delivery quality gate (v0.7): the gate.* Schema config, fail-loud validation, the four-phase runner (deterministic requirements/tests folds + forked consistency/local reviewers), the dsh-auto-review weak dependency (durable autoReview/* verdict records; degrade-to-local), the /gate status|run|config command, the durable doublecheck/gate fold, and the doublecheck.gate settings namespace.
  • src/guard/prose.ts — the injected reminder/deny/review/gate prose, per-language (en / zh); gate notices open with a one-sentence role statement and stay short.
  • src/domain/ — pure folds and vocabularies shared by both rows (stages, evidence, vagueness, vocabulary, report, gate). No Cordis imports.
  • src/events.ts — process-local Cordis event vocabulary (@mode emit, observability-only) + the durable doublecheck/state and doublecheck/gate SessionEventMap members and the doublecheck-gate message source.
  • skills/ — four bundled discipline skills (grill-requirements, red-green-tdd, delivery-review, delivery-proof), each <name>/SKILL.md in the generic Agent Skills layout.
  • tests/ — vitest; real Cordis Context with scripted services (subagents/commands) and synthetic durable events; tests/fixtures/ holds real-transcript regression logs.
  • scripts/ — session-log tooling (decode-session, extract-fixture, scan-sessions) + release-notes.mjs (extracts the top changelog section for the publish workflow's release job).

Read the full file on GitHub · 46 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. 2d ago First seen · 46 lines · 1,522 tokens per session scan A 46d095844be7

Subscribe to this mod's changes

dsh-doublecheck AGENTS.md is an instructions file published in the GitHub repository PerryLink/dsh-doublecheck (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,522 tokens to every session, about $0.0076 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.

Code reviewPlanningWriting and docsdeepseek-harnessdshdsh-pluginengineering-disciplineguardrequirements
Related

Other instructions, from other repositories

DSH-better-sidebar AGENTS.md

AGENTS.md instructions for omdsh-dev/DSH-better-sidebar, covering dsh-better-sidebar 仓库规则（agents）, 1. 仓库硬约束（必须遵守）, 2. ci 挂载冒烟（plugin-mount job / pnpm test:mount）, 3. dsh 0.1.2-alpha 适配要点（alpha 通道） and 4. npm 发版（github release → npm publish）.

omdsh-dev/DSH-better-sidebar · 3,150 tokens

dsh-worktable AGENTS.md

Instructions for Aisland-SJL/dsh-worktable, covering dsh-worktable 项目规则, 协作方式（用户定案，最高优先级）, 边界, 构建与验证 and 领域约定（会话中必须遵守）.

Aisland-SJL/dsh-worktable · 4,863 tokens

awesome-dsh-plugin AGENTS.md

Instructions for beancookie/awesome-dsh-plugin, covering agents.md, 内容来源（source of truth）, 目录结构（每个文件夹的作用）, 添加插件 and 整理流程（分类与数量）.

beancookie/awesome-dsh-plugin · 2,209 tokens

awesome-deepseek-harness-plugins AGENTS.md

Instructions for imsai-sh/awesome-deepseek-harness-plugins, covering repository instructions, the submission gate is the product, generated files, cross-repo contracts (no ci spans both repositories) and permanent urls.

imsai-sh/awesome-deepseek-harness-plugins · 1,057 tokens

dsh-config-manager AGENTS.md

Instructions for xiajiajun516/dsh-config-manager, covering agents.md — dsh config manager 仓库协作指南, 🗣️ 语言与交流, 📦 项目概览, 🗂️ 仓库结构与职责 and ui 分层（改动前必读，避免放错层）.

xiajiajun516/dsh-config-manager · 7,380 tokens

dsh-mcp-panel AGENTS.md

Instructions for PerryLink/dsh-mcp-panel, covering agents.md, layout, hard rules applied here, config and build.

PerryLink/dsh-mcp-panel · 1,748 tokens