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/ohswedd/praxis/taskgit clone --depth 1 https://github.com/Ohswedd/praxisWhat 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 | $0.00029 | $0.00332 |
| Opus 5 | $0.00015 | $0.00166 |
| Sonnet 5 | $0.00006 | $0.00066 |
| Haiku 4.5 | $0.00003 | $0.00033 |
Grade A, and why
task 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.
What it actually says
Use the task-orchestrator skill to deliver this request end-to-end:
${ARGUMENTS}
Spec-only mode. If the request starts with spec:, or asks for a spec, a plan,
or an estimate rather than a change, run Phase 1 alone: use the prompt-architect
skill to produce goal, in-scope, out-of-scope/non-goals, acceptance criteria,
assumptions, and open questions, then stop and present it. Surface ambiguity and
any scope you would exclude; never narrow it silently. Ask only genuinely blocking
questions, and otherwise state the assumption you would proceed under. Keep it
proportional to the task.
Otherwise run every phase in order. Do not jump to editing: restructure into a spec (prompt-architect), investigate the code and confirm the CLAUDE.md, plan in plan mode before touching files, implement to code-craft standard, run the full quality rubric (every vertical including completeness) fixing each finding, update the living knowledge, and finish with the canonical structured report.
Nothing is left implicit: no placeholders, no silent scope cuts, no missing
pieces. If the request touches user-facing surface, the frontend-pipeline skill
wraps these phases and the report is not green without the two UI verticals.
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 · 27 lines · 29 tokens per session scan A d82db098bc3a
task is a command published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 332 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.
Other commands, from other repositories
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
stop
Stop the voice dictation daemon.
wp-clone
Clone a remote or staging WordPress site to a local development environment.
wp-tailwindify
Convert an HTML/CSS demo to Tailwind-native HTML — preserves section delimiters, maps colors to @theme variables.
ui-audit
Comprehensive UI audit for accessibility, consistency, and usability.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.