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 commands/px0-ai/px0/guidelinesgit clone --depth 1 https://github.com/px0-ai/px0What 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 | $0.00000 | $0.01358 |
| Opus 5 | $0.00000 | $0.00679 |
| Sonnet 5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
guidelines 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
px0 guidelines
Guidelines are Markdown files describing how you work — how you word a commit message, what your Go reviews check. Workflows inline them verbatim, so output comes back in your voice instead of the model's default.
You do not create them. px0 workflows new decides whether the workflow it is
building leans on a durable convention the store has no file for, drafts it, and
lists it on the workflow — see
guidelines the build writes. What is
here are the operations on a file that already exists.
Implemented by px0/guidelines.py (the file format), px0/authoring.py (the
files) and px0/claims.py (claim identity and history).
The file
A guideline is frontmatter over rules, the same shape as a skill:
---
name: commit-messages
description: How to word a commit message. Use when the workflow writes or rewrites one.
---
## Imperative mood summary line
Write the summary line in the imperative mood: "Add retry logic", not "Added".
Keep it under 72 characters and drop the trailing period.
## Explain why, not what
The diff already shows what changed. Use the body to explain why.
| Field | What it is for |
|---|---|
name |
The guideline's name, which is its filename. A folder groups a topic (code-review/go.md is named go) and is not part of the name |
description |
One sentence: what the convention covers and when a workflow should follow it. This is the only thing px0 workflows new matches a new workflow against, so it decides whether the file is ever attached |
| body | The rules, as ## sections. This is what a run inlines — the frontmatter never reaches the model |
The description is the whole reason this file has frontmatter. Matching on the
body instead attached commit-messages.md to a nightly standup that only
reads commits: the words overlapped, the conventions did not.
A file with no frontmatter still works — the name falls back to its filename and
the description to its first rule — but it will rarely be picked, and
px0 doctor lists it under guideline_descriptions. Add the two lines with
px0 guidelines edit <name>.
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 First seen · 179 lines · 0 tokens per session scan A 371cf141e75c
guidelines is a command published in the GitHub repository px0-ai/px0 (241 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,358 tokens. 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 commands, from other repositories
wiki-ingest
Ingest a source document into the LLM Wiki.
README
This folder gathers the project's 9 slash commands in a single place. Each command file specifies its traversal pattern (which Layer × Cycle cells it passes through, and in which cycle-stage flow) plus the Human Reviewer Gate. The nature of each role and the Layer × Cycle matrix have their SoT in…
wiki-discover
Discover unexpected connections in the LLM Wiki (Memex serendipity).
wiki-news
Search for latest news related to the LLM Wiki's key topics.
wiki-query
Query the LLM Wiki and synthesize an answer.
wiki-export
Export wiki to merged files for Claude.ai Project Knowledge.