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.
npx agentmods add instructions/everclear077/dsh-progressive-tools/agents-mdgit clone --depth 1 https://github.com/everclear077/dsh-progressive-toolsWrote 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/instructions/everclear077/dsh-progressive-tools/agents-md)<a href="https://agentmods.dev/instructions/everclear077/dsh-progressive-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/everclear077/dsh-progressive-tools/agents-md.svg" alt="Measured on agentmods" 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 | $0.00794 | $0.00794 |
| Opus 5 | $0.00397 | $0.00397 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
dsh-progressive-tools 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 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.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
Guidance for coding agents working in this repository. Human contributors should also read CONTRIBUTING.md.
Project overview
dsh-progressive-tools is a DeepSeek Harness (DSH) plugin that provides
cache-stable progressive tool discovery. The default stable-proxy mode keeps
a small byte-stable tool surface (tool_search, tool_dispatch, and a few
always-visible tools) on every request, holds the complete tool catalog in
process memory, and executes discovered tools through the ordinary DSH
execution pipeline. A legacy dynamic mode natively activates whole tool
families at the cost of cache stability.
Layout
| Path | Purpose |
|---|---|
src/index.ts |
Plugin entry: config resolution, tool registration, prompt projection, routing guard, lifecycle events |
src/catalog.ts |
Catalog construction, wildcard matching, BM25-style tool search, group ranking |
src/state.ts |
Dynamic-mode activation state: LRU eviction, turn expiry, snapshots |
src/defaults.ts |
Default config values, always-visible patterns, built-in family rules |
src/types.ts |
Shared public types |
tests/ |
Vitest suites, including a real AgentLoop request regression test |
docs/ |
Architecture, configuration reference, progressive disclosure model |
cordis.patch.yml |
Bundle composition patch consumed by the DSH plugin loader |
Commands
pnpm install # install dependencies (pnpm 11, Node 22.19+ or 24+)
pnpm run typecheck # tsc --noEmit
pnpm run lint # oxlint src tests
pnpm run test # vitest run
pnpm run build # tsc -p tsconfig.build.json -> lib/
pnpm run check # typecheck + lint + test + build + publint (run before finishing)
Invariants that must not break
- The first AgentLoop request already carries the small stable surface.
- Discovery never changes the top-level tool list, system text, or generated Code Mode SDK for an unchanged composition. The AgentLoop integration test asserts byte-level prefix equality; keep it passing.
- Deferred tools execute through the full DSH pipeline (
ctx.tools.executewith the dispatcher token as parent), so approval, guards, validation, timeouts, and result policy still apply. - Direct calls to deferred names stay denied by the monotonic guard. Any new deferred path must be covered by the guard and by an end-to-end test.
- All runtime behavior uses public DSH services and events. Per-agent state stays isolated and every effect is reversible for unload and reload.
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.
- 3d ago First seen · 73 lines · 794 tokens per session scan A eeb4344b81b5
dsh-progressive-tools AGENTS.md is an instructions file published in the GitHub repository everclear077/dsh-progressive-tools (2 stars, last pushed 7d ago), licensed MIT. It adds 794 tokens to every session, about $0.0040 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 2026-08-31.
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 适配要点（0.1.2-rc.1+ 基线） and 4. npm 发版（github release → npm publish）.
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）.
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.
dsh-mcp-panel AGENTS.md
Instructions for PerryLink/dsh-mcp-panel, covering agents.md, layout, hard rules applied here, config and build.
dsh-enhanced-plugins AGENTS.md
Instructions for sky-unicorn/dsh-enhanced-plugins, covering agents.md — deepseek harness 插件项目通用规则, 权威来源与开始工作前的检查, 插件架构与职责边界, cordis 插件与生命周期 and 配置与 settings.
awesome-deepseek-harness-plugins CLAUDE.md
Instructions for imsai-sh/awesome-deepseek-harness-plugins, a project described as: DeepSeek Harness plugin store, marketplace and hub — 11,000+ dsh plugins with search, rankings, install commands and a free public API. DeepSeek Harness 插件市场 / 插件商店：自动收集与格式校验，免费搜索 API。deepseek1024.com.