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 skills add krzysztofsurdy/code-virtuoso --skill stakeholder-update-writergit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/skills/krzysztofsurdy/code-virtuoso/stakeholder-update-writer)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/stakeholder-update-writer"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/stakeholder-update-writer/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.
<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/stakeholder-update-writer"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/stakeholder-update-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00947 |
| Opus 5.5 | $0.00014 | $0.00379 |
| Sonnet 5.5 | $0.00007 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
stakeholder-update-writer 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 yesterday.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stakeholder update message
Write a concise stakeholder update message for Slack or email.
Process
1. Gather context
Find out what the user wants to communicate. The source can be anything:
- An epic or set of tickets from your ticket tracker or project management tool (fetch through your project tracker integration if available)
- A conversation summary or decision outcome
- A project milestone, blocker, or risk
- A release status or go/no-go decision
- Anything the user describes or provides
If the context is about tracked work (epic, sprint, tickets), fetch the relevant data first. If it's about a decision, event, or general update, work from what the user provides.
2. Understand the audience and purpose
Before drafting, identify:
- Who is receiving this (team, management, cross-functional stakeholders, external partners)
- What they need to know (status, decision, blocker, request for input, FYI)
- What action is expected from them (none, approval, input, awareness)
If unclear, ask the user briefly before drafting.
3. Draft the message
Tone: Direct and confident, with no corporate filler. Write as a person talking to colleagues.
Structure: Flowing text with minimal formatting. Use bold for section headers only when they help. Avoid:
- Bullet-point walls
- Listing every ticket or task individually
- Project management jargon (sprint velocity, story points, epics)
- Explaining the obvious
Content flow:
- One-line context: what this is about
- Background: what led to this update (brief, only what the reader needs)
- The substance: grouped by theme, not by ticket or task. Summarize what matters in plain language. Keep it to 3-4 groups at most.
- Framing: set expectations on effort, timeline, or impact
- Dependencies or asks: who needs to do what
- Next steps: where to find details, when to expect the next update, an offer to discuss
Key principles:
- Lead with the conclusion, not the process
- Group by business theme, not by task or ticket
- Say what needs to happen, not what the task title says
- Name people/teams who own dependencies
- One link to a tracking board or document is enough. Don't link every item
- Keep it under 200 words if possible
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.
- yesterday Changed · -1 lines e7d20c5e7e7f
- 6d ago Changed · +1 tokens per session 9d4fea019dbb
- 1mo ago First seen · 104 lines · 34 tokens per session scan A 489994a5d721
stakeholder-update-writer is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (36 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 947 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
trello
Manage Trello boards, lists, and cards via the Trello REST API.
survey
A project-discovery workflow that creates `.claude/context.md`, a shared file describing the project's purpose, design, constraints, and measures of success.
hermes-overnight-autonomy
Use for unattended Hermes continuity and watchdogs.
dev-plan
Full development planning pipeline. Orchestrates a team of agents (researcher, prd-writer, software-architect, project-planner, issue-estimator) to take a project idea from concept to sprint-ready issues.
github-issues
Create, search, triage, and manage GitHub issues. Each section shows gh first, then the curl fallback.