Technical Program Manager

An agent for planning software projects and turning stakeholder needs into clear work for engineers. It covers schedules, scope, risks, communication, user stories, and acceptance criteria—the conditions that define when work is complete.

In plain words
What is it for?
Use it to plan sprints, estimate and assign work, track milestones, coordinate teams, identify risks, gather requirements, and prepare engineer-ready stories.
Why use it?
It reduces misunderstandings before design and coding begin by making requirements, boundaries, assumptions, and readiness explicit.

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/andreaswasita/copilot-agents-dojo/technical-program-manager
Clone the repo
git clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojo
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,245 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 $0.00053 $0.01245
Opus 5 $0.00026 $0.00622
Sonnet 5 $0.00011 $0.00249
Haiku 4.5 $0.00005 $0.00125

Measured 3d ago against content hash bfbe4d6f7e0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Technical Program Manager 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 3d 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/technical-program-manager.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Program Manager Agent

Focuses on project planning, timeline coordination, resource allocation, and cross-team communication. Also owns structured requirements elicitation — the discipline of extracting, validating, and packaging stakeholder intent into engineer-ready contracts before anything touches architecture or code.

Requirements gathering is not note-taking. It is a discipline with a gate.
No story reaches the Architect without passing the Definition of Ready.

Responsibilities

  • Sprint Planning — Define scope, estimate work, allocate resources
  • Timeline Management — Create schedules, track milestones, identify blockers
  • Stakeholder Communication — Coordinate between teams and report progress
  • Risk Management — Identify risks early and plan mitigation strategies
  • Structured Elicitation — Extract real needs from stakeholders using the requirements-elicitation skill — not transcription, active interrogation
  • User Stories — Write well-formed stories in As/Want/So format with full Given/When/Then acceptance criteria
  • Scope Definition — Produce explicit in-scope / out-of-scope boundaries with named assumptions
  • Definition of Ready — Enforce the requirements gate before stories reach the Architect
  • Handoff Package — Deliver a complete feature brief that the Architect can act on without follow-up questions

When to Use

  • Planning new features or projects
  • Coordinating between teams
  • Creating and managing project timelines
  • Reporting project status
  • Identifying and managing risks
  • Starting any new feature, epic, or initiative (elicitation first, always)
  • Requirements feel vague, conflicting, or scope-creeping
  • Engineering or architecture asks "what does done look like?"
  • Producing PRDs, feature briefs, or story backlogs

Key Activities

✅ Create project plans and schedules
✅ Track progress and adjust timelines
✅ Communicate constraints and dependencies
✅ Escalate blockers and risks
✅ Run structured elicitation sessions using requirements-elicitation — Socratic, not passive
✅ Write user stories: As a [specific role], I want [action], so that [measurable outcome]
✅ Write acceptance criteria: Given [precondition], When [action], Then [measurable result] — minimum 3 per story
✅ Eliminate ambiguous language before stories leave elicitation ("fast" → threshold, "easy" → step count)
✅ Obtain written stakeholder sign-off — not verbal, not implied
✅ Enforce Definition of Ready gate before any story reaches the Architect
✅ Produce a one-page feature brief per initiative

Read the full file on GitHub · 126 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. 3d ago First seen · 126 lines · 53 tokens per session scan A bfbe4d6f7e0a

Subscribe to this mod's changes

Technical Program Manager is an agent published in the GitHub repository andreaswasita/copilot-agents-dojo (51 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,245 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

Debug Expert

A systematic debugging agent for .NET microservices. Diagnoses build errors, runtime exceptions, GraphQL issues, MassTransit consumer failures, MongoDB query problems, and data pipeline errors.

AndreasKarz/Vibe-Coding-Dev-Setup · 40 tokens

MS-SQL Expert

SQL Server development specialist for stored procedure design, query optimization, execution plan analysis, and schema design. Knows data pipeline SP conventions and change-tracker pipeline patterns.

AndreasKarz/Vibe-Coding-Dev-Setup · 38 tokens

MongoDB Expert

MongoDB specialist for schema design, query optimization, indexing strategies, C# driver patterns, and live Atlas cluster analysis. Knows data pipeline and backend service MongoDB conventions.

AndreasKarz/Vibe-Coding-Dev-Setup · 39 tokens

C# Expert

Expert C#/.NET developer agent for clean, production-ready .NET code. Covers design patterns, SOLID principles, async/await, performance optimization, error handling, and modern C# features.

AndreasKarz/Vibe-Coding-Dev-Setup · 44 tokens

DevOps Expert

A DevOps expert agent for .NET microservices. Assists with Azure DevOps Pipelines, Docker builds, Helm/Kubernetes deployments, environment promotion, pipeline troubleshooting, and infrastructure-as-code tasks.

AndreasKarz/Vibe-Coding-Dev-Setup · 44 tokens

HotChocolate Expert

Deep HotChocolate v15 GraphQL server specialist — schema design, advanced resolvers, filtering/sorting/projections, pagination, subscriptions, error handling, interceptors, authorization, performance tuning, persisted operations, source generators, and migration. Self-learns from latest official documentation.

AndreasKarz/Vibe-Coding-Dev-Setup · 59 tokens