Borrowing it
Nothing to install: this file belongs to weijiafu14/pi2dsh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/weijiafu14/pi2dsh/main/AGENTS.mdgit clone --depth 1 https://github.com/weijiafu14/pi2dshWrote 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/weijiafu14/pi2dsh/agents-md)<a href="https://agentmods.dev/instructions/weijiafu14/pi2dsh/agents-md"><img src="https://agentmods.dev/badge/instructions/weijiafu14/pi2dsh/agents-md/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/instructions/weijiafu14/pi2dsh/agents-md"><img src="https://agentmods.dev/badge/instructions/weijiafu14/pi2dsh/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00663 | $0.00663 |
| Opus 5.5 | $0.00265 | $0.00265 |
| Sonnet 5.5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
pi2dsh 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 2mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Architecture mapping is a required deliverable
pi2dsh is both an ecosystem bridge and an executable architecture test for DeepSeek Harness.
Any agent changing compatibility behaviour must follow the single mapping standard in
docs/architecture-mapping-standard.md.
Architecture knowledge is maintained as ordinary Markdown, not a JSON ledger or generated verdict.
Use docs/architecture-mapping-matrix.md for the evolving
Pi/DSH branches, docs/plugin-validation-matrix.md for real
plugin evidence, and docs/dsh-architecture-conformance.md
for conclusions. Do not create a parallel taxonomy. src/compatibility.ts is the leaf-level runtime
inventory, not an architectural verdict by itself.
Required model
Organize Pi as capability domain → capability contract → concrete interface, and DSH as architecture domain → carrying mechanism → public seam. Concrete leaves are an open inventory: add newly found interfaces and modules under the appropriate branch, and revise the abstraction when a leaf does not fit. Counts such as 111 Pi rules or 45 DSH subsystems are versioned observations, never invariants or proof of completeness.
The theoretical mapping compares five semantic dimensions: user goal, intervention timing, authoritative state, lifecycle and native presentation. Matching names are not sufficient.
Required validation
Every real plugin validation references existing mapping IDs and traces five layers:
Pi call → pi2dsh translation → public DSH seam → DSH authority → user-visible/restorable result
Grade each mapping independently:
- native;
- reliable translation;
- sidecar/workaround;
- degraded or missing;
- host-specific and not scored.
Do not give a whole package one blanket result when it exercises multiple capabilities.
Required attribution
- A suitable public DSH seam exists but the bridge has not used it: pi2dsh debt.
- The correct data or decision point is outside every public seam, with a real consumer and a
minimal reproduction: confirmed DSH gap and a stable
DSH-ARCH-*ID. - A terminal/CLI implementation should be re-expressed for DSH rather than copied: host difference.
- A theoretical mapping without a real plugin run: theoretically viable, not yet verified.
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.
- 2mo ago First seen · 68 lines · 663 tokens per session scan A a196ebd064d9
pi2dsh AGENTS.md is an instructions file published in the GitHub repository weijiafu14/pi2dsh (214 stars, last pushed 2d ago), licensed MIT. It adds 663 tokens to every session, about $0.0027 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.