A workflow for handing bounded coding work or one-time verification to Claude as a worker. It stores the goal, workspace, budget, verifier, schedule, status, and evidence for each run.

Use it to delegate coding, run authorized tests, schedule supported work, or check the status of an ongoing handoff. It is also for preserving evidence and requiring human approval for irreversible decisions.

It prevents delegated work from starting without a clear acceptance check or from exceeding the approved scope. It also lets you pause, resume, stop, or inspect a run without claiming that fresh verification happened.

prax-shift — Skill for Claude Code by ChanningLua/prax-agent

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.

Any agent

npx skills add ChanningLua/prax-agent --skill prax-shift

Clone the repo

git clone --depth 1 https://github.com/ChanningLua/prax-agent

Made for: Claude Code.

Or install prax, the plugin that ships this one along with the rest of its 5 skills, 4 commands, 1 agent.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/channinglua/prax-agent/prax-shift/github.svg)](https://agentmods.dev/skills/channinglua/prax-agent/prax-shift)

Your own site

<a href="https://agentmods.dev/skills/channinglua/prax-agent/prax-shift"><img src="https://agentmods.dev/badge/skills/channinglua/prax-agent/prax-shift/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/channinglua/prax-agent/prax-shift"><img src="https://agentmods.dev/badge/skills/channinglua/prax-agent/prax-shift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,226 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.01226
Opus 5.5	$0.00028	$0.00490
Sonnet 5.5	$0.00014	$0.00245
Haiku 4.5	$0.00007	$0.00123

Measured 1mo ago against content hash dfb70be43208, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prax-shift 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 1mo 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.

src/prax/assets/claude/skills/prax-shift/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prax Shift for Claude

Use Shift as one Prax operating mode. Prax owns durable state, verification, approval boundaries, scheduling, and evidence; Claude is a replaceable worker.

Map the user's intent

For start or handoff, require a bounded goal, verifier, workspace, and budget.
For test-only handoff, use the one-shot verification path below; planning or integration work alone does not authorize test execution.
For status, use prax shift status --run-id <id> to inspect saved evidence in .prax/harness-runs/<id>/, without starting work or claiming fresh verification.
For continuing coding work, resume the frozen contract with the same run ID. One-shot verification cannot resume.
For pause or stop, persist a pause request and preserve evidence. Remove a schedule only when explicitly requested.
Create a recurring schedule only when explicitly requested.

Operating contract

Keep intent, irreversible decisions, production actions, and scope changes HITL.
Execute AFK only inside the requested workspace and budget.
Require an independent verifier for coding work. Without one, report the missing acceptance criterion and do not start a coding worker.
Keep Claude at dontAsk: operations that still require approval are denied. This is not an OS sandbox. Do not bypass permissions to keep AFK work going; missing narrowly preauthorized capabilities require a human decision.
Never auto-push, auto-merge, deploy, spend money, or widen permissions.
Treat HARNESS-ERROR as an environment failure, not a code defect.

Coding: prepare and run

Prepare the files for the user after inspecting existing configuration. Do not overwrite another task or unrelated work. In .prax/harness.json, use schemaVersion: 1, worker: "claude", and relevant existing policy_files (or []); optional model is frozen too. Preserve an existing worker choice unless the user asks to change it.

Create .prax/task.json with schemaVersion: 1, a unique id, the agreed goal, and kind: "code-check". Declare repositories with workspace-relative path, the actual current branch, and narrow relative scope arrays. Declare verifier with trusted argv, workspace-relative cwd, and timeout_seconds; use explicit pytest test paths. Optional control_files binds additional existing scripts/fixtures using workspace-relative paths. Keep acceptance outside editable scope. Set budget with max_iterations, wall_seconds, stuck_after; default conservatively to 3, 600, 2 when unspecified and disclose these limits.

Read the full file on GitHub · 118 lines

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.

1mo ago First seen · 118 lines · 71 tokens per session scan A dfb70be43208

Subscribe to this mod's changes

prax-shift is a skill published in the GitHub repository ChanningLua/prax-agent (272 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,226 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-12.

Building agents Planning

prax-shift next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
prax-shiftChanningLua/prax-agent	Skill	272	1mo ago	MIT	A	71	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code