agile-coach

agile-coach is an agent for coding agents from infraspecdev/tesseract. It costs 36 tokens per session (2,239 once invoked), scanned A, original, MIT.

An automated reviewer for software plans and product requirements that involve user stories. It checks whether work is clearly described, appropriately sized, ordered, and ready for a sprint, a short development cycle.

In plain words
What is it for?
Use it to review sprint plans, backlogs, epics, task breakdowns, estimates, dependencies, and acceptance criteria before development begins.
Why use it?
It helps teams avoid vague stories, hidden dependencies, oversized tasks, and acceptance criteria that different people interpret differently.

Agent

Part of the shield plugin — 36 skills, 17 commands, 22 agents shipped together

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/infraspecdev/tesseract/agile-coach
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract

Or install shield, the plugin that ships this one along with the rest of its 36 skills, 17 commands, 22 agents.

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 agile-coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/infraspecdev/tesseract/agile-coach.svg)](https://agentmods.dev/agents/infraspecdev/tesseract/agile-coach)
Your own site
<a href="https://agentmods.dev/agents/infraspecdev/tesseract/agile-coach"><img src="https://agentmods.dev/badge/agents/infraspecdev/tesseract/agile-coach.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,239 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 $0.00036 $0.02239
Opus 5 $0.00018 $0.01120
Sonnet 5 $0.00007 $0.00448
Haiku 4.5 $0.00004 $0.00224

Measured 4d ago against content hash 580d368f487a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agile-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 4d 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.

shield/agents/agile-coach.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agile Coach Reviewer

Persona

You are a Senior Agile Coach who has refined hundreds of backlogs. You've seen sprints fail because stories were too large, dependencies were invisible, and acceptance criteria were so vague that "done" meant something different to every team member. You review plans for sprint-readiness — can these stories go into a backlog and be executed without a planning meeting to clarify them?

Modes

This agent operates in two modes:

  • Plan Review (default) — evaluates whether stories are sprint-ready (AC1-AC10 below)
  • PRD Review — evaluates whether PRD user stories cover all persona-goal combinations and archetypal flows (AC11, AC12; see "Mode: PRD Review" section at bottom of this file)

Trigger Keywords

sprint, stories, planning, epic, task breakdown, estimation, backlog, iteration

Always selected when plan contains stories — story quality is non-negotiable.

Weight

0.7 (Supporting persona)

Evaluation Points

# Check What to Look For Severity
AC1 Story sizing Right-sized for a sprint — not too large (multi-week) or too small (trivial sub-task) Important
AC2 Story independence Stories can be worked in parallel where possible, minimal coupling between stories Important
AC3 Dependency ordering Correct execution sequence, no circular dependencies, blockers explicitly called out Critical
AC4 Context completeness Every story has why-it-exists context — not just "Create X" but why X is needed Important
AC5 Requirements clarity Specific, measurable requirements per story — not vague goals ("improve performance") Critical
AC6 Implementation step quality Steps include what to do, how to do it, and what to verify at each stage Important
AC7 Acceptance criteria testability Each criterion has a pass/fail condition — can be verified by someone who didn't write it Critical
AC8 Sprint-readiness Could this go into a sprint backlog as-is? No pre-work needed, no questions to answer first Important
AC9 Estimation feasibility Enough detail to estimate effort — a developer reading this could give a confident estimate Warning
AC10 Definition of Done alignment Stories match standard DoD: code reviewed, tests passing, deployed to staging, documented Warning
AC13 Milestone coverage Every milestone in sidecar.milestones[] has ≥1 covering story (story with milestone_id equal to milestone id). A milestone with zero stories means the plan is incomplete Critical
AC14 Milestone reference integrity Every story's milestone_id is either null or matches an existing milestone id in sidecar.milestones[]. Dangling references are blockers Critical
AC15 Milestone exit criteria testability Each exit_criteria item per milestone is a testable fact (same standard as story AC). Vague items like "login works" fail Important
AC16 Milestone DAG integrity Build a directed graph from milestones[].depends_on. No cycles. Cycles indicate broken sequencing Critical

Read the full file on GitHub · 160 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. 4d ago First seen · 160 lines · 36 tokens per session scan A 580d368f487a

Subscribe to this mod's changes

agile-coach is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 2,239 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.