What is my-pi-nopeek?

A procedure for running commands that need credentials without exposing secret values such as passwords or API keys. It uses the nopeek command-line tool to limit which environment variables a child command can access.

Checking credential names, running authenticated commands with an allowlist, and auditing secret exposure and ignore rules.

It reduces the chance of putting secrets into agent context, command arguments, logs, or source control, while noting that programs can still print them.

my-pi-nopeek — Skill for Claude Code and Codex by spences10/my-pi

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 spences10/my-pi --skill my-pi-nopeek

Clone the repo

git clone --depth 1 https://github.com/spences10/my-pi

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/spences10/my-pi/my-pi-nopeek/github.svg)](https://agentmods.dev/skills/spences10/my-pi/my-pi-nopeek)

Your own site

<a href="https://agentmods.dev/skills/spences10/my-pi/my-pi-nopeek"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/my-pi-nopeek/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/spences10/my-pi/my-pi-nopeek"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/my-pi-nopeek.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 402 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	$0.00026	$0.00402
Opus 5.5	$0.00010	$0.00161
Sonnet 5.5	$0.00005	$0.00080
Haiku 4.5	$0.00003	$0.00040

Measured 2d ago against content hash c8efbccbcc5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

my-pi-nopeek 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.

packages/pi-tool-guidance/skills/my-pi-nopeek/SKILL.md · 42 lines

What it actually says

Credential-dependent commands

Use the nopeek CLI to reduce accidental disclosure. This skill does not install hooks, load credentials automatically, or guarantee safe output.

Inspect key names with pnpx nopeek list or pnpx nopeek status; never read secret files into model context.
In pnpm projects use pnpx nopeek; otherwise use npx nopeek.

Prefer one-shot execution with an explicit key allowlist:

pnpx nopeek run .env --only DATABASE_URL -- sh -c 'psql "$DATABASE_URL" -c "select 1"'

Keep variable expansion inside the child shell. Do not print keys, run env/printenv, enable tracing, or place secret values in arguments.
Review what the child command prints: nopeek cannot prevent arbitrary applications from leaking credentials through stdout or stderr.
Use nopeek load only with confirmed persistent harness injection, or when loading and execution happen in the same trusted shell. A source-file result does not persist into another Pi tool call.
Use pnpx nopeek audit for exposure and gitignore checks.

Pi's redaction extension is a separate best-effort safety net, not a security boundary. If secret output is unavoidable, stop and agree on a safer workflow rather than exposing it.

The CLI must be available through the user's package runner or installed locally. Do not change their credential storage or configuration implicitly. See nopeek's threat model.

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.

2d ago First seen · 42 lines · 26 tokens per session scan A c8efbccbcc5c

Subscribe to this mod's changes

my-pi-nopeek is a skill published in the GitHub repository spences10/my-pi (139 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 402 once invoked, about $0.0001 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 2026-11-02.

LLM Security TypeScript cli coding-agent mcp pi

bun

Read before a js eval cell that spawns a process, server or PTY, installs a package, or starts a long run, and before any bun -e, script, server, CLI, test, typecheck, format, bundle, or package-management work: this session's eval js kernel runs Bun 1.4+. Bun 1.4.x builtins replace 20+ npm deps and dev tools — check…

code-yeongyu/senpi · 237 tokens

pi

Use when you need a minimal, extensible terminal AI coding agent harness in TypeScript — npm @earendil-works/pi-coding-agent 1.4.0, extensions/skills/prompt templates, multi-provider (OpenAI/Anthropic/Google) routing, container isolation (Docker/Gondolin/OpenShell); also for pi: command not found, Node >=22.19.0…

znlgis/opengis-skills · 103 tokens

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens

semantic-compression

Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…

can1357/oh-my-pi · 77 tokens

optimization

Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.

1jehuang/jcode · 52 tokens

gpt-image-gen

MUST read before generating images. Prompt-crafting guide for gpt-image-2.5 covering tool routing (native imagegeneration server tool vs the generateimage tool), model and quality selection, prompt structure, exact text rendering, reference-image editing, transparent assets, output formats, and multi-turn refinement.

code-yeongyu/senpi · 66 tokens