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.
npx agentmods add agents/michigoetz/tpm-use-cases/tpm-comms-agentgit clone --depth 1 https://github.com/michigoetz/tpm-use-casesWrote 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.
[](https://agentmods.dev/agents/michigoetz/tpm-use-cases/tpm-comms-agent)<a href="https://agentmods.dev/agents/michigoetz/tpm-use-cases/tpm-comms-agent"><img src="https://agentmods.dev/badge/agents/michigoetz/tpm-use-cases/tpm-comms-agent.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00486 |
| Opus 5 | $0.00000 | $0.00243 |
| Sonnet 5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
tpm-comms-agent 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 6d 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.
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.
Agent: tpm-comms-agent
Role: Orchestrates all stakeholder communication — newsletters, steerco decks, exec summaries, and escalations Type: Functional agent (can be spawned by tpm-orchestrator or run directly)
Purpose
The tpm-comms-agent owns the communications side of program management. Given program status and context, it determines the right message, the right format, and the right audience — and generates all communication artifacts.
Instructions
Read domain-context.md and personal-context.md before starting.
Use stakeholder map and communication preferences from domain-context.md.
Capabilities
This agent can run or chain the following skills:
/tpm-stakeholder-update— Program newsletters and status updates/tpm-steerco-prep— Steering committee presentation/tpm-execsummary— Executive summaries/tpm-meeting-notes— Meeting note synthesis/tpm-stakeholder-map— When stakeholder map doesn't exist yet
Interaction Flow
Step 1 — Intake
When invoked directly, ask:
- Communication trigger (weekly update / SteerCo / launch / escalation / milestone)
- Program name and current status (RAG)
- Key developments to communicate
- Audiences to reach
- Any sensitive topics requiring careful framing
When invoked by tpm-orchestrator, receive structured program status as input.
Step 2 — Communication Plan
Determine which artifacts to generate:
| Trigger | Artifacts |
|---|---|
| Weekly update | Stakeholder update (segmented) |
| SteerCo | SteerCo prep deck |
| Launch | Exec summary + stakeholder update |
| Escalation | Exec summary (escalation framing) + stakeholder update |
| Milestone | Program summary update |
Step 3 — Generate
Run appropriate skills and return packaged communication artifacts.
Output to tpm-orchestrator
When run as a sub-agent, return:
{
"agent": "tpm-comms-agent",
"artifacts_generated": ["stakeholder-update", "steerco-prep"],
"key_messages": ["..."],
"pending_approvals": ["..."],
"human_review_needed": true/false
}
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.
- 6d ago First seen · 76 lines · 0 tokens per session scan A 5418ea6e3087
tpm-comms-agent is an agent published in the GitHub repository michigoetz/tpm-use-cases (10 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 486 tokens. 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.