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/zseta/progi/agents-mdgit clone --depth 1 https://github.com/zseta/progiWhat 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 | $0.01887 | $0.01887 |
| Opus 5 | $0.00944 | $0.00944 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
progi 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 yesterday.
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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
What this is
Progi is an MCP-native workflow engine. Key terms:
- workflow: a reusable template of ordered steps; defines a repeatable, reused across many tasks
- step: one unit of work in a workflow; has a playbook, an input spec, and an output spec
- playbook: markdown attached to a step; the agent reads it via
start_or_continue_taskand follows it - task: a single execution of a workflow; progresses through steps one at a time with lifecycle
todo→in_progress→done
Two interfaces over one SQLite DB:
- Progi MCP server (FastMCP, stdio) — the work loop runs here, inside the user's harness.
- Progi Monitoring (FastAPI + Jinja + Alpine/AlpineAJAX) — a web app for tracking tasks and reviewing workflows.
The one rule
All database access goes through progi/db.py. MCP tools and web routes
are thin adapters that call named functions there — they never write SQL. This is
what keeps LLM-driven and human-driven edits behaviorally identical.
Layout
| File | Role |
|---|---|
progi/db.py |
Schema (SQLAlchemy Core) + all queries, mutations, and state-transition logic |
progi/mcp_server.py |
@mcp.tool wrappers (work loop + workflow authoring) |
progi/web/app.py |
FastAPI routes → Jinja partials |
progi/prompts/ |
Pass 1 / Pass 2 authoring system prompts (served by tools) |
progi/seed.py |
"Blog Post" workflow + sample task (idempotent) |
tests/test_db.py |
DB roundtrip, full work loop, authoring |
Frontend / UI components
Templates live in progi/web/templates/. The UI stack is:
- Tailwind CSS v4 (compiled by the standalone CLI via
just build) - Alpine.js v3 + Alpine AJAX — vendored to
static/vendor/byjust vendorize - PenguinUI — a copy-paste component library; no install needed
Using PenguinUI
Browse components at https://www.penguinui.com/components, pick what you need, and paste the HTML directly into a template. There is nothing to download or import — PenguinUI components are just Tailwind + Alpine markup.
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.
- yesterday First seen · 176 lines · 1,887 tokens per session scan A 3204b6fe2040
progi AGENTS.md is an instructions file published in the GitHub repository zseta/progi (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,887 tokens to every session, about $0.0094 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
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
codeTree CLAUDE.md
Instructions for ThinkyMiner/codeTree, covering claude.md, what this is, structural analysis tools (13), graph & onboarding tools (10) and supported languages.
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.
plan-forge testing.instructions.md
Testing rules for Plan Forge — vitest patterns, fake-timers vs tolerance, mocking conventions, and how to read test output without hallucinating failures. Auto-loads when editing test files.