Borrowing it
Nothing to install: this file belongs to moliver28/corpus-kb. 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/moliver28/corpus-kb/master/AGENTS.mdgit clone --depth 1 https://github.com/moliver28/corpus-kbWrote 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/moliver28/corpus-kb/agents-md)<a href="https://agentmods.dev/instructions/moliver28/corpus-kb/agents-md"><img src="https://agentmods.dev/badge/instructions/moliver28/corpus-kb/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/moliver28/corpus-kb/agents-md"><img src="https://agentmods.dev/badge/instructions/moliver28/corpus-kb/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 | $0.03940 | $0.03940 |
| Opus 5.5 | $0.01576 | $0.01576 |
| Sonnet 5.5 | $0.00788 | $0.00788 |
| Haiku 4.5 | $0.00394 | $0.00394 |
Grade A, and why
corpus-kb 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Corpus-KB Agent Instructions
Repository Layout (read first)
Single source tree; all new code goes in src/corpus_kb/. Commands below run from the repo root.
src/corpus_kb/— active Python package (packaged default config atsrc/corpus_kb/config.yaml)tests/— root-level pytest suiteconfig.yaml— root runtime configsrc/corpus_kb/migrations/— idempotent SQL migrationsscripts/— backward-compat shimssrc/corpus_kb/_setup/— installer, migration runner, config validatorui_src/— TypeScript SPA source (React 19 +antd6,pnpm)src/corpus_kb/ui_dist/— built SPA assets served at/app/
Quick Reference
pip install -e ".[dev]" # install (editable)
ruff check src/ tests/ # lint (ruff — NOT flake8/black)
ruff format --check src/ tests/
pyright src/ # type-check (pyright — NOT mypy; basic mode per pyrightconfig.json)
python src/corpus_kb/_setup/validate_configs.py # validate MCP configs pre-push
python scripts/schema_parity_gate.py # schema parity, both migration sets (sqlglot, static; poe schema-parity)
python src/corpus_kb/_setup/validate_profiles.py # profile gate: schema + strategy/template/seeds cross-refs (poe validate-profiles)
python -m pytest tests/ -v --tb=short --durations=10 # tests (Ollama up, nomic-embed-text pulled)
pytest --cov=corpus_kb --cov-report=term-missing # coverage
CLI
corpus-kb → corpus_kb.cli:app:
corpus-kb setup --dry-run # preview (docker compose, database, migrations, models)
corpus-kb setup # apply
corpus-kb doctor # read-only diagnostics
corpus-kb start --transport http --port 8010
Old scripts/install.py is a deprecation shim delegating to corpus_kb._setup.install.
Toolchain
Build: setuptools (not hatch/poetry), packages in src/. Lint/type-check tools: see Quick Reference.
CI (.github/workflows/ci.yml)
Gate order: lint (ruff check src/ tests/, no deps) → type-check (pyright src/, project deps installed) → validate-configs (command above) → test (ubuntu/windows/macos: Ollama + python -m pytest tests/ from repo root).
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.
- 2d ago Changed · +43 tokens per session 1c7164df169b
- 4d ago Changed · +2 lines · +121 tokens per session fc9b5ff801fe
- 6d ago Changed · +135 tokens per session 5ce5cfa5fc49
- 7d ago Changed · +60 tokens per session 495b9b5ca08b
- 9d ago Changed · +1 lines · +145 tokens per session cb29bbba4465
- 10d ago Changed · +4 lines · +204 tokens per session 067a2cada506
- 12d ago Changed · -69 lines · -1,002 tokens per session scan C → A d8e477bede50
- 13d ago Changed · +3 lines · +33 tokens per session 76549a85f9da
- 14d ago Changed · +3 lines · +108 tokens per session 977aa2baa531
- 19d ago First seen · 209 lines · 4,093 tokens per session scan C e74f62acee0c
corpus-kb AGENTS.md is an instructions file published in the GitHub repository moliver28/corpus-kb (1 stars, last pushed today), licensed MIT. It adds 3,940 tokens to every session, about $0.0158 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 2026-08-31.
corpus-kb AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| corpus-kb AGENTS.mdmoliver28/corpus-kb | Instructions file | 1 | today | MIT | A | 3,940 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |