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/guilhembusset/agentic-or-workshop/agents-mdgit clone --depth 1 https://github.com/GuilhemBusset/agentic-or-workshopWrote 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/guilhembusset/agentic-or-workshop/agents-md)<a href="https://agentmods.dev/instructions/guilhembusset/agentic-or-workshop/agents-md"><img src="https://agentmods.dev/badge/instructions/guilhembusset/agentic-or-workshop/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 | $0.00711 | $0.00711 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
agentic-or-workshop 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 5d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Purpose
This repo is used to teach agentic coding to PhD students in optimization research.
Environment and Toolchain
This project is uv-managed and uses mise for Python version management.
- Python compatibility is
>=3.12(requires-python). - Workshop shells are pinned to
3.12via.mise.tomland.python-version. - Use
uvfor setup, dependency management, and command execution. - Do not use
pip installor manualvenvcommands for normal workflow.
Project Shape
- There is no single
main.pyentrypoint at the repository root. - Most runnable scripts live under
workshop/materials/**/run_*.py. - Tests live under
tests/andworkshop/materials/**/tests/. - Non-regression coverage lives in
tests/non_regression/.
Task-Scoped Navigation (Workshop Rule)
- Treat the user prompt as the navigation boundary.
- Only explore files/directories explicitly mentioned in the prompt.
- If the prompt says "work in
abc/", only read/edit withinabc/and its children. - Do not run repository-wide discovery commands (
rg --files,find ., broadls -R) unless explicitly requested. - If additional context outside the boundary is required, stop and ask for permission before expanding scope.
- If no path is provided, ask the user for the target folder/file before exploring.
- Prefer targeted commands, for example:
ls abcrg "pattern" abcuv run pytest abc/tests
Standard Workflow
- Activate
misein your shell. - Sync environment:
uv sync - Run target script:
uv run python <path-to-runner.py> - Add a dependency:
uv add <package> - Add a dev dependency:
uv add --dev <package> - Update lockfile after dependency changes:
uv lock - Format code:
uv run ruff format . - Lint code:
uv run ruff check . - Type check code:
uv run ty check
Testing
- Preferred framework:
pytest. - Place tests in
tests/orworkshop/materials/**/tests/with namestest_*.py. - Run the full suite with:
uv run pytest - Run non-regression checks with:
uv run pytest tests/non_regression -q - When possible, run targeted tests first (
uv run pytest <path>), then the full suite.
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.
- 5d ago First seen · 65 lines · 711 tokens per session scan A fa4d00c421d9
agentic-or-workshop AGENTS.md is an instructions file published in the GitHub repository GuilhemBusset/agentic-or-workshop (2 stars, last pushed 5mo ago), licensed MIT. It adds 711 tokens to every session, about $0.0036 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
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
AGENTS.md instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
agentic-ai-engineering-course AGENTS.md
AGENTS.md instructions for towardsai/agentic-ai-engineering-course, covering the what and course map (lessons ↔ code projects).
anki-mcp-server CLAUDE.md
Claude Code instructions for nailuoGG/anki-mcp-server, covering claude.md, repository overview, development commands, build & development and install dependencies.