Borrowing it
Nothing to install: this file belongs to ask33r/omp-dsh-workers. 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/ask33r/omp-dsh-workers/main/AGENTS.mdgit clone --depth 1 https://github.com/ask33r/omp-dsh-workersWrote 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/ask33r/omp-dsh-workers/agents-md)<a href="https://agentmods.dev/instructions/ask33r/omp-dsh-workers/agents-md"><img src="https://agentmods.dev/badge/instructions/ask33r/omp-dsh-workers/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/ask33r/omp-dsh-workers/agents-md"><img src="https://agentmods.dev/badge/instructions/ask33r/omp-dsh-workers/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 | $0.00762 | $0.00762 |
| Opus 5.5 | $0.00305 | $0.00305 |
| Sonnet 5.5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
omp-dsh-workers 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 1mo 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DSH — agent instructions
An oh-my-pi (OMP) extension: an OMP session acts as director and spawns
persistent DeepSeek-Harness workers (dsh --profile headless) via dsh_spawn /
dsh_wait, relaying their results back as native chat messages. README.md
carries the full tool table, error codes and install steps.
Stack
TypeScript on Bun for extensions/, dependency-free plain Node ≥22 ESM for
tools/dsh-bridge/, Biome 2.5.10 for lint and format. Bun is the package
manager — there is no npm/yarn/pnpm lockfile.
Commands
bun run check— Biome lint + formatbun run typecheck—tsc --noEmitbun run test— unit + integration + bridge suites.github/workflows/test.ymlis the ground truth for CI order and env
Invariants
- Never run a bare
bun testfrom the repo root. Bun'smock.module()is process-global, soextensions/dsh-taskmocks leak into the bridge's Node tests and turnkill(pid)intokill(-1)— inside a container that kills the whole session. The reason is recorded inbunfig.toml, andtools/dsh-bridge/test/node-only.jsis the second guard. Use thetest:*scripts. - Run tests with an isolated
$HOME. Three tests once passed only by accident, reading the developer's real~/.ompand~/.dsh. tools/dsh-bridge/stays dependency-free and build-step-free. Do not add dependencies, a bundler or TypeScript there.- The repository is the source of truth: install scripts only symlink live directories back into it, and abort rather than overwrite a real file.
- The language split is deliberate — everything a human or a model reads is English, in-code comments and test names are Russian. Do not "fix" it.
- No concrete model id is ever hardcoded — not as a default, not as a fallback.
The executor model is resolved at runtime: the
modelargument ofdsh_spawn/dsh_task→ the@dshrole (modelRoles.dsh) → the session'sctx.model→ nothing passed, so DSH falls back to its ownagent-default-model(extensions/dsh-task/role-model.ts;tools/dsh-bridge/src/run.jsowns the threeDSH_MODEL*env keys and clears them on every run). Real ids belong in local configs only — outside the repo. Inside it they may appear as test fixtures and as<provider>/<model>[:<effort>]notation examples in docs, nowhere else.
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.
- 1mo ago First seen · 59 lines · 762 tokens per session scan A a17fd78e3127
omp-dsh-workers AGENTS.md is an instructions file published in the GitHub repository ask33r/omp-dsh-workers (1 stars, last pushed 28d ago), licensed MIT. It adds 762 tokens to every session, about $0.0030 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 2026-09-30.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.