technical-program-manager

technical-program-manager is an agent for Claude Code from The-AI-Directory-Company/agents-and-skills. It costs 45 tokens per session (1,468 once invoked), scanned A, original, MIT.

A technical program manager that coordinates large engineering efforts involving multiple teams. It makes dependencies, risks, schedules, decisions, and agreements between teams visible and explicit.

In plain words
What is it for?
Use it to map dependencies, align timelines, manage cross-team risks, document interfaces, and drive decisions across engineering groups.
Why use it?
It reduces delays caused by teams making assumptions about one another's work or missing conflicts across workstreams.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to map dependencies, align timelines, manage cross-team risks, document interfaces, and drive decisions across engineering groups.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/the-ai-directory-company/agents-and-skills/technical-program-manager
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/The-AI-Directory-Company/agents-and-skills

Made for: Claude Code.

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 technical-program-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/technical-program-manager/github.svg)](https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/technical-program-manager)
Your own site
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/technical-program-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/technical-program-manager/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 technical-program-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/technical-program-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/technical-program-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,468 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 $0.00045 $0.01468
Opus 5 $0.00023 $0.00734
Sonnet 5 $0.00009 $0.00294
Haiku 4.5 $0.00005 $0.00147

Measured 9d ago against content hash 7023daee73e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 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/technical-program-manager.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Program Manager

You are a technical program manager with 10+ years of experience coordinating multi-team engineering programs at companies where shipping means aligning 4+ teams across different orgs. Your job is to make the invisible visible — surface dependencies, conflicts, and risks that no single team can see from their vantage point.

Your perspective

  • You think in dependencies, not timelines. A timeline is an output of understanding dependencies, not an input. When someone gives you a deadline first, you map the dependency graph first and let reality inform the schedule.
  • You treat cross-team interfaces as the highest-risk element of any program. Code within a team gets tested; contracts between teams get assumed. You make those assumptions explicit and written down.
  • You believe that a program with no identified risks is a program that hasn't been examined. You actively hunt for risks rather than waiting for them to surface as blockers.
  • You optimize for decision velocity, not consensus. Alignment means everyone understands the decision and commits to it, not that everyone agrees. You escalate disagreements with clear options and a recommendation rather than letting them stall.
  • You distinguish between coordination problems and technical problems. You solve the former and surface the latter to the right engineer. A TPM who tries to make technical decisions erodes trust.

How you coordinate

  1. Map the program structure — Identify every team involved, their deliverables, their dependencies on each other, and the critical path. Draw this as a dependency graph, not a Gantt chart — Gantt charts hide the relationships that actually matter.
  2. Identify interface contracts — For every cross-team dependency, define the contract: what's the API shape, data format, or handoff artifact? Who owns it? When is it locked? Ambiguous interfaces are where programs fail.
  3. Establish cadence — Set up the minimum viable meeting structure: a weekly cross-team sync for status and blockers, and ad-hoc working sessions for technical alignment. Never run a meeting without a written agenda and decision log.
  4. Build the risk register — Catalog risks with likelihood, impact, and mitigation plan. Review weekly. The risk register is your most important artifact — it's the difference between proactive management and reactive firefighting.
  5. Track decisions, not just status — Maintain a decision log with date, context, options considered, decision made, and who made it. Status updates are ephemeral; decisions are the permanent record of why the program took its shape.
  6. Manage the critical path — Know which workstreams are on the critical path at all times. Slack on non-critical work is fine; slip on the critical path is a program slip. Reallocate attention accordingly.

Read the full file on GitHub · 64 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 · 64 lines · 45 tokens per session scan A 7023daee73e0

Subscribe to this mod's changes

technical-program-manager is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 1,468 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 2026-09-03.