What is pi-cli-repro?

A repository-specific workflow for reproducing problems through the real Pi command-line program. Pi is a command-line tool for running coding-agent interactions, and the workflow can inspect extension loading, prompts, requests, and Anthropic sign-in behavior.

Use it to reproduce Pi extension bugs, investigate Anthropic OAuth failures, inspect prompt or request changes, and validate fixes through the live command-line path.

It helps reveal problems that may not appear in unit tests, especially when the installed command-line program differs from the development libraries. It also keeps reproduction runs quick and focused.

How gotgenes/pi-anthropic-auth configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to gotgenes/pi-anthropic-auth. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gotgenes/pi-anthropic-auth/main/.pi/skills/pi-cli-repro/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/gotgenes/pi-anthropic-auth

Made for: Claude Code, Codex.

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/gotgenes/pi-anthropic-auth/pi-cli-repro.svg)](https://agentmods.dev/skills/gotgenes/pi-anthropic-auth/pi-cli-repro)

Your own site

<a href="https://agentmods.dev/skills/gotgenes/pi-anthropic-auth/pi-cli-repro"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/pi-cli-repro.svg" alt="Measured on agentmods" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 658 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	$0.00048	$0.00658
Opus 5	$0.00024	$0.00329
Sonnet 5	$0.00010	$0.00132
Haiku 4.5	$0.00005	$0.00066

Measured 8d ago against content hash 2d8ca3bce356, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pi-cli-repro 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 8d 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.

.pi/skills/pi-cli-repro/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pi CLI Repro

Use When

You need to reproduce a bug through the real pi executable.
Extension logic must be validated in the live CLI path rather than only unit tests.
Anthropic OAuth behavior differs between tests and the installed CLI.
You need a short feedback loop for prompt shaping or request-shaping changes.

Core Workflow

1. Reproduce with explicit extension loading

Use the live CLI with this extension file loaded directly:

pi \
  --model anthropic/claude-haiku-4-5 \
  --no-session \
  --tools read,grep,find,ls \
  -e /Users/chris/development/pi/pi-anthropic-auth/src/index.ts \
  -p "How many lines are in @AGENTS.md ?"

Why this shape:

--no-session avoids session carryover noise
--tools read,grep,find,ls keeps repros narrow and read-only
-e .../src/index.ts guarantees the local extension is actually loaded
-p gives a fast non-interactive cycle
anthropic/claude-haiku-4-5 is the preferred fast repro model unless you are chasing a model-specific issue

2. Check version alignment first

Before trusting a repro, confirm the installed CLI version:

pi --version

If the live CLI version does not match the Pi libraries this repo targets, treat that as a possible source of mismatch.

Useful Experiments

Compare default prompt vs minimal custom prompt

If Anthropic OAuth fails, test whether the default Pi prompt is the trigger:

PI_ANTHROPIC_AUTH_DEBUG=tool-use pi ... -p "hi"

then compare with:

pi ... --system-prompt "You are a coding assistant." -p "hi"

If the minimal prompt succeeds while the default prompt fails, suspect prompt fingerprinting.

Remove project context from the experiment

To separate prompt-template issues from AGENTS.md or repo guidance:

pi ... --no-context-files -p "hi"

Decision Rules

When a live CLI repro fails:

Confirm the installed pi version.
Determine whether the failure tracks with:
- the default Pi prompt
- project context files
- request payload shape
- tool-use sequencing
Fix the problem in the shallowest extension seam that can solve it.

Read the full file on GitHub · 94 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.

8d ago First seen · 94 lines · 48 tokens per session scan A 2d8ca3bce356

Subscribe to this mod's changes

pi-cli-repro is a skill published in the GitHub repository gotgenes/pi-anthropic-auth (237 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 658 once invoked, about $0.0002 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 2026-08-30.

Debugging OAuth authentication pi pi-package

surf

Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.

w-winter/dot314 · 60 tokens

provider-setup

Reports which delegation CLIs are installed and authenticated, installs missing ones, and stores the result. Use before delegating or when a provider errors.

athola/claude-night-market · 33 tokens

prose-review

Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…

w-winter/dot314 · 84 tokens

text-search

Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.

w-winter/dot314 · 22 tokens

repoprompt-tool-guidance-refresh

Refresh RepoPrompt tool guidance when the CLI/MCP surface changes. Tracks RepoPrompt CE (rpce-cli, the maintained target) across versions, and can diff the frozen Classic CLI (rp-cli) against CE. Uses /.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh to capture/diff --help and -l (tool…

w-winter/dot314 · 115 tokens

pixiv-cli-ci

Diagnose, verify, monitor, and safely operate pixiv-cli GitHub Actions runs and local CI gates, including PR Quality gate, workflow policy, platform smoke, native/browser evidence, release handoffs, and approved reruns. Use when checks fail or hang, a PR needs readiness verification, a workflow run needs root-cause…

FlanChanXwO/pixiv-cli · 82 tokens

pi-anthropic-auth: Skill for Claude Code