Borrowing it
Nothing to install: this file belongs to gintasz/unigent. 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/gintasz/unigent/main/AGENTS.mdgit clone --depth 1 https://github.com/gintasz/unigentWrote 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/gintasz/unigent/agents-md)<a href="https://agentmods.dev/instructions/gintasz/unigent/agents-md"><img src="https://agentmods.dev/badge/instructions/gintasz/unigent/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/gintasz/unigent/agents-md"><img src="https://agentmods.dev/badge/instructions/gintasz/unigent/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 | $0.00550 | $0.00550 |
| Opus 5.5 | $0.00220 | $0.00220 |
| Sonnet 5.5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
unigent 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup — do this FIRST in any fresh checkout or worktree
A new git worktree has no node_modules. Before editing, building, or committing, bootstrap it:
corepack pnpm install --frozen-lockfile
Core vs. adapter
Unigent core MUST house all reusable language/runtime logic. Private harness adapters and the unigent-cli frontend contain only the minimum translation and presentation glue. Public SDK consumers import the bundled facade from unigent-sdk.
Constitution
Read CONSTITUTION.md before starting any codebase changes or evaluations.
Validation
When a code change is completed, always run full workspace tests, not just unit tests, not just package tests.
corepack pnpm run typecheck # types only, no tests
corepack pnpm test # deterministic suite (unit + fake). Excludes e2e.
corepack pnpm run test:tui # deterministic terminal rendering and 5,000-run stress suite
corepack pnpm run test:e2e # real Pi, Claude CLI, and Codex CLI calls; requires local model authentication
corepack pnpm run build
corepack pnpm run check # FAST static tier (typecheck, format, lint, lint:types, ast) — what pre-commit runs
corepack pnpm run check:full # FULL DoD gate (adds arch, spell, deps, dead, dup, build, api-surface, coverage) — what pre-push runs
Live E2E skips only when a backend is unavailable. A red authenticated run is a regression.
Releases
The two public packages in scripts/release-packages.mjs (unigent-sdk and unigent-cli) use one lockstep version. Private workspace packages carry the same version but are bundled rather than published. Before pushing
a vX.Y.Z tag, update every package manifest, version literal, lockfile, and CHANGELOG.md; run the
deterministic validation above, excluding live E2E unless the user explicitly requests it; then
commit and push the matching tag. .github/workflows/release.yml is the normal publish entrypoint:
it publishes to latest through npm trusted publishing and verifies fresh-cache
SDK and global CLI installs. Monitor the workflow and confirm both packages' latest tags before
reporting success. Do not manually publish or change dist-tags during a normal release. A package's
first-ever release is the only exception: publish it interactively once, configure trusted
publishing for that new npm package, then push the tag so the workflow verifies the artifacts.
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 · 41 lines · 550 tokens per session scan A a546cb654b2d
unigent AGENTS.md is an instructions file published in the GitHub repository gintasz/unigent (102 stars, last pushed 15d ago), licensed MIT. It adds 550 tokens to every session, about $0.0022 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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.