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 skills/anthropics/knowledge-work-plugins/compose-outreachnpx skills add anthropics/knowledge-work-plugins --skill compose-outreachgit clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsWrote 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/anthropics/knowledge-work-plugins/compose-outreach)<a href="https://agentmods.dev/skills/anthropics/knowledge-work-plugins/compose-outreach"><img src="https://agentmods.dev/badge/skills/anthropics/knowledge-work-plugins/compose-outreach.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 | $0.00045 | $0.01181 |
| Opus 5 | $0.00023 | $0.00590 |
| Sonnet 5 | $0.00009 | $0.00236 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
compose-outreach 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- compose-outreach — 100% identical, 0 lines differ
- compose-outreach — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose Outreach
Generate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signals for a specific company or contact.
Outreach Process
Step 1: Look Up the Target
Use Common Room MCP tools to find and retrieve data for the target (company and/or specific contact). Pull:
- Recent product activity and engagement signals
- Community activity (posts, questions, reactions)
- 3rd-party intent signals (job postings, news, funding)
- Relationship history (prior contact, meetings, email opens)
If the user specified a person, run contact-level research. If only a company was given, identify the best contact to target based on title, engagement, and role.
Step 2: Web Search for External Hooks (If CR Signals Are Thin)
If CR returned strong signals (recent activity, engagement, product usage), those should drive personalization — skip web search. If CR signals are thin or the prospect has little CR activity, run a web search for external hooks:
What to search:
"[company name]" funding OR acquisition OR launch OR announcement— last 30 days"[contact full name]" "[company name]"— look for recent articles, interviews, LinkedIn posts, or conference talks
Prioritize external hooks that are:
- Very recent (< 2 weeks) — the prospect is likely still thinking about it
- Publicly visible — they know you could have seen it
- Change-signaling — growth, new role, new product, new market
If the user explicitly asks for web search or external hooks, run it regardless of CR signal richness.
Step 3: Spark Enrichment (If Available)
If Spark is available, run enrichment on the target contact to get persona classification, background, and influence signals. Use this to calibrate tone and message angle.
Step 4: Identify the Best Hooks
From the signal data, identify the 1–3 strongest personalization hooks. Rank by:
- Recency — happened in the last 7–14 days
- Specificity — a concrete action they took, not a general trend
- Relevance — connects directly to a value your product delivers
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 136 lines · 45 tokens per session scan A 6bba827598fc
compose-outreach is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,849 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 1,181 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…