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 commands/softaworks/agent-toolkit/compose-emailgit clone --depth 1 https://github.com/softaworks/agent-toolkitWhat 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 | $0.00028 | $0.00902 |
| Opus 5 | $0.00014 | $0.00451 |
| Sonnet 5 | $0.00006 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
compose-email 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
1 near-identical copy found in the catalogue:
- compose-email — 91% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Professional Email
Generate a professional, well-structured email using communication best practices for software developers.
Arguments
$ARGUMENTS - Optional context, topic, or existing draft to refine
Workflow
Step 1: Gather Context
If $ARGUMENTS is empty or insufficient, use AskUserQuestion to gather:
Question 1: Recipient Type (header: "Audience")
- Technical peer (developer, engineer)
- Non-technical stakeholder (PM, executive, customer)
- Cross-functional team (mixed audience)
- Manager or leadership
Question 2: Email Purpose (header: "Purpose")
- Status update or progress report
- Request (review, approval, resources)
- Information sharing (FYI, announcement)
- Escalation or raising concern
- Following up on prior conversation
Question 3: Urgency (header: "Urgency")
- Urgent - needs response today
- Standard - within 1-2 days
- Low priority - for awareness only
Step 2: Apply Communication Framework
Use the What-Why-How structure:
-
WHAT (Opening - 1-2 sentences)
- Lead with the key message or request
- State the purpose immediately
- No throat-clearing ("I hope this email finds you well...")
-
WHY (Context - 2-3 sentences)
- Provide necessary background
- Explain relevance to the recipient
- Include only essential context
-
HOW (Action - clear next steps)
- Specific call-to-action
- Clear deadline if applicable
- Who needs to do what
Step 3: Apply Email Best Practices
Subject Line:
- Specific and scannable (5-8 words ideal)
- Include action needed: "[Action Required]", "[FYI]", "[Decision Needed]"
- Include deadline if urgent: "[Due Friday]"
Body Structure:
- Bullets for multiple points (3-5 max)
- Bold key information
- One topic per email
- Short paragraphs (2-3 sentences max)
Tone Calibration by Audience:
| Audience | Tone | Jargon Level |
|---|---|---|
| Technical peer | Direct, precise | High (use technical terms) |
| Non-technical | Business-focused | Low (translate jargon) |
| Cross-functional | Balanced | Medium (explain as needed) |
| Leadership | Concise, impact-focused | Low (focus on outcomes) |
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 · 145 lines · 28 tokens per session scan A ea6c231a80e5
compose-email is a command published in the GitHub repository softaworks/agent-toolkit (2,401 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 902 once invoked, about $0.0001 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.
Other commands, from other repositories
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
speckit.opsmill.retrospect
Run a session retrospective that surfaces context-management gaps and routes them to approved follow-up actions.
create-issue
Transform feature descriptions, bug reports, or improvement ideas into well-structured GitHub issues.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.