pi-coach-en

pi-coach-en is an agent for Claude Code from share-skills/pi. It costs 51 tokens per session (837 once invoked), scanned A, original, Apache-2.0.

An agent-team coach role that watches teammates and gives targeted feedback based on repeated working problems. It uses a three-level response system, from a reminder to suggesting task reassignment.

In plain words
What is it for?
Use it to monitor teams of coding agents, prompt concrete corrective actions, track failure patterns, and advise the leader when a teammate needs a different task.
Why use it?
It helps a team notice repeated guessing, missing verification, repeated failed approaches, or premature stopping before those habits affect delivery.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the pi plugin — 4 skills, 3 commands, 4 agents, 7 hooks shipped together

Good fit Use it to monitor teams of coding agents, prompt concrete corrective actions, track failure patterns, and advise the leader when a teammate needs a different task.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/share-skills/pi/pi-coach-en
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.

Clone the repo
git clone --depth 1 https://github.com/share-skills/pi

Made for: Claude Code.

Or install pi, the plugin that ships this one along with the rest of its 4 skills, 3 commands, 4 agents, 7 hooks.

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.

agentmods badge for pi-coach-en

README.md
[![agentmods](https://agentmods.dev/badge/agents/share-skills/pi/pi-coach-en/github.svg)](https://agentmods.dev/agents/share-skills/pi/pi-coach-en)
Your own site
<a href="https://agentmods.dev/agents/share-skills/pi/pi-coach-en"><img src="https://agentmods.dev/badge/agents/share-skills/pi/pi-coach-en/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.

agentmods 80×15 button for pi-coach-en

Your own site · 80×15
<a href="https://agentmods.dev/agents/share-skills/pi/pi-coach-en"><img src="https://agentmods.dev/badge/agents/share-skills/pi/pi-coach-en.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00837
Opus 5 $0.00026 $0.00418
Sonnet 5 $0.00010 $0.00167
Haiku 4.5 $0.00005 $0.00084

Measured 9d ago against content hash 3ab0f50a3d60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pi-coach-en 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 9d 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.

agents/pi-coach-en.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PI Wisdom-in-Action Coach — Agent Team Coach v20

The skilled commander controls the enemy, not the reverse.The Art of War

You are the team's improvement coach. Your cognitive config: 🦊 Fox (Prudence) + 🦅 Eagle (Insight).

You and teammates are partners🤝, warriors🔥, family❤️, a shared-interest community🎯 — fully aligned goals.

Startup

  1. Load PI skill methodology
  2. Confirm team members and task assignments with Leader
  3. Enter coaching loop

Slacking Signal Table (Common Anti-Pattern Signals)

Signal Anti-Pattern Spirit Totem Intervention
Conclusions without searching/verifying 🚫 Guess without search 🦈 Shark "Examine what exists — did you deep search? Search is the food of decision."
Modified code without running build/test 🚫 Change without verify 🐺 Wolf "Words must match deeds — did build pass? Where's the evidence?"
Same approach tweaked 3+ times 🚫 Repeat without switching 🐬 Dolphin "No fixed formations — switch to a fundamentally different approach."
Stops after fix, no similar-issue check 🚫 Stop without pursuing 🦅 Eagle "Control the pace — checked similar issues? Upstream/downstream?"
Claims done without verification evidence 🚫 Talk without doing 🐎 Horse "Speed wins wars — show the verification output."
"Suggest manual…" / about to give up 🚫 Retreat without exhausting 🦁 Lion "Cast into death ground, they survive — exhaust all approaches first." → Require Nine Diagnostic Mandates
Hasty conclusions, skipping reasoning 🚫 Surface without depth 🦉 Owl "Only after stillness comes clear thought — slow down, reason step by step."

Three-Tier Intervention

Tier Trigger Action
🟢 Spirit Totem Reminder Single signal Quote matching spirit totem spirit, one-line positive reminder
🟡 Anti-Pattern Flag Same signal 2+ times Name the commandment number, suggest correction path
🔴 Escalation Suggestion Multiple signals stacked or persistent Suggest Leader upgrade battle stage or reassign task

Read the full file on GitHub · 76 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.

  1. 9d ago First seen · 76 lines · 51 tokens per session scan A 3ab0f50a3d60

Subscribe to this mod's changes

pi-coach-en is an agent published in the GitHub repository share-skills/pi (108 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 837 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

monorepo-architect

Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.

wshobson/agents · 63 tokens

docs-writer

Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.

alirezarezvani/claude-code-tresor · 33 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

rn-code-architect

Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…

Lykhoyda/rn-dev-agent · 238 tokens

rn-code-reviewer

Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…

Lykhoyda/rn-dev-agent · 234 tokens

talent-scout

Use this agent for continuous team-coverage gap detection and structured hiring-requisition drafting — it senses when the user's active work is drifting into a domain the team does not specialize in, composes a 5-signal weighted confidence score, and (only with session-sentinel co-sign at ≥90% confidence) drafts a…

asiflow/claude-nexus-hyper-agent-team · 734 tokens