config

A command for viewing or changing this repository's Praxis settings, including workspace mode and automation options. It shows where each active value comes from, such as an environment variable or repository file.

In plain words
What is it for?
Use it to check or toggle owner or contributor workspace mode, auto-pilot, auto-merge, auto-bootstrap, and the quality gate.
Why use it?
Project settings can come from several places and may be difficult to trace when they conflict or seem unexpected. This reports the value actually in force for the session.

Command

Part of the praxis plugin — 15 skills, 8 commands, 13 agents, 5 hooks shipped together

Install

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.

agentmods
npx agentmods add commands/ohswedd/praxis/config
Clone the repo
git clone --depth 1 https://github.com/Ohswedd/praxis

Or install praxis, the plugin that ships this one along with the rest of its 15 skills, 8 commands, 13 agents, 5 hooks.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00698
Opus 5 $0.00013 $0.00349
Sonnet 5 $0.00005 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 2d ago against content hash 8aec6263c9c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

config 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.

plugins/praxis/commands/config.md · 45 lines

What it actually says

Run the settings command and report the result:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/config.py" ${ARGUMENTS:-status}

Each setting resolves environment variable, then repo toggle file, then .praxis.toml, then (for mode) detection, and the output names the source, so a value that surprises the user can always be traced. Read the output rather than assuming: what it prints is what is in force for the rest of the session.

  • mode is the one setting that is not on/off. owner means praxis maintains this project's CLAUDE.md, .claude/settings.json, /docs, CHANGELOG.md and ADRs as committed files. contributor means the repository is not ours: the brief is CLAUDE.local.md, settings are .claude/settings.local.json, praxis config is .claude/.praxis/praxis.toml, and /docs, CHANGELOG.md, docs/adr/ and docs/design/ are updated only if the repo already has them, otherwise kept under .claude/.praxis/knowledge/. All of it is git-excluded, and nothing praxis authors goes near a commit. auto (the default) infers it from the repo's git history. Switching also adds or removes the praxis block in $GIT_COMMON_DIR/info/exclude.
  • auto-pilot ON: ask no design or approach questions. Do your own QA, resolve each decision with the best-practices skill, and record every non-trivial one under "Decisions taken autonomously" in the report. Stop only for a hard external blocker such as a missing credential.
  • auto-merge ON: after a green audit and passing checks, self-review the diff and merge the PR. OFF means open the PR and leave the merge to a human. It never applies in contributor mode: merging is the maintainers' call.
  • bootstrap ON (the default): a repo praxis has not set up is bootstrapped first, in the same turn, before the work starts. OFF leaves the repo without a brief or guardrails until the user runs /praxis:bootstrap themselves.
  • gate OFF: the Stop hook no longer holds the turn open. Say so plainly when you hand work back, because nothing else will.

A toggle file is a local, uncommitted choice. For a decision the whole team should share, put it in .praxis.toml and commit it; in contributor mode put it in .claude/.praxis/praxis.toml, which layers on top and stays local. Safety guards and the secret and destructive-command blocks stay active whatever these are set to, as does the refusal to stage a praxis local artifact.

Changes

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.

  1. 2d ago First seen · 45 lines · 26 tokens per session scan A 8aec6263c9c2

Subscribe to this mod's changes

config is a command published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 698 once invoked, about $0.0001 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.