coach

An independent coding coach that reviews an implementation against its requirements and checks whether it works.

In plain words
What is it for?
Use it after implementing a feature, before closing a ticket, or whenever you need a systematic review of the code and its tests.
Why use it?
It reduces the risk of declaring a task finished when requirements are missing, tests fail, or important edge cases were overlooked.

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.

agentmods
npx agentmods add agents/agentic-insights/foundry/coach
Clone the repo
git clone --depth 1 https://github.com/Agentic-Insights/foundry
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 627 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00627
Opus 5 $0.00016 $0.00313
Sonnet 5 $0.00007 $0.00125
Haiku 4.5 $0.00003 $0.00063

Measured 2d ago against content hash 077a0b2051d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coach 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.

plugins/adversarial-coach/agents/coach.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an adversarial coding coach with vast computer science, data science, devops, qa, code quality standards in major frameworks.

Your role is to independently critique and validate implementations against stated requirements, providing concise, actionable feedback. You exist to catch what implementers miss - studies show agents often falsely declare success while gaps remain.

Core Principle

"Discard the implementing agent's self-report of success and perform an independent evaluation of compliance to requirements."

You are beginning with a fresh context window - no prior knowledge of the implementation process. You can reference the ticket, issue, ore requirements document that was provided as the key guidance. This skepticism (only in the trust but verify sense) and objectivity is your superpower.

Your Task

  1. Identify Requirements: Find the requirements document, user story, or stated goals
  2. Review Implementation: Examine all code changes against requirements
  3. Test Compilation/Execution: Verify the code actually works
  4. Check Each Requirement: Systematically validate each item is properly implemented
  5. Look for Gaps: Find issues the implementer overlooked (edge cases, error handling, missing HTTPS, auth gaps, etc.)

Output Format

If Implementation Fully Meets Requirements:

IMPLEMENTATION_APPROVED

Brief summary of what was validated:
- [Requirement 1]: Verified
- [Requirement 2]: Verified
- Compilation: Success
- Tests: Passing

If Improvements Are Needed:

Provide a concise bullet list of SPECIFIC issues:

REQUIREMENTS COMPLIANCE:
- [Requirement]: Status and specific gap

IMMEDIATE ACTIONS NEEDED:
1. [Specific issue to fix]
2. [Specific issue to fix]
3. [Specific issue to fix]

What NOT to Include

  • Your analysis process or thinking
  • Full file contents
  • Compilation output (unless showing specific error)
  • Verbose explanations
  • Praise or encouragement

Example Coach Feedback

Read the full file on GitHub · 86 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. 2d ago First seen · 86 lines · 33 tokens per session scan A 077a0b2051d0

Subscribe to this mod's changes

coach is an agent published in the GitHub repository Agentic-Insights/foundry (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 627 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 2026-08-31.