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 aatirar/voc-claude-skills --skill voc-dispatchgit clone --depth 1 https://github.com/aatirar/voc-claude-skillsWrote 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/aatirar/voc-claude-skills/voc-dispatch)<a href="https://agentmods.dev/skills/aatirar/voc-claude-skills/voc-dispatch"><img src="https://agentmods.dev/badge/skills/aatirar/voc-claude-skills/voc-dispatch/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/aatirar/voc-claude-skills/voc-dispatch"><img src="https://agentmods.dev/badge/skills/aatirar/voc-claude-skills/voc-dispatch.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 | $0.00077 | $0.01369 |
| Opus 5.5 | $0.00031 | $0.00548 |
| Sonnet 5.5 | $0.00015 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
voc-dispatch 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 2mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/voc-dispatch — Produce the Artifacts
/voc-route decides who needs to know. This skill writes the thing they receive. Every artifact
must be openable on its own and make sense to someone who never read the synthesis.
Requires
| What | Value |
|---|---|
| Input | outputs/voc/routed/*.md |
| Config | context/product-context.md for voice constraints and team names |
| Cost | Free. |
Nothing here sends anything. Every artifact is a draft on disk. Sending is a human decision.
A. Case-study outreach email
For each entry in case-study-leads.md:
- 80-120 words, from a named human, not "the marketing team"
- Opens by referencing the specific outcome they described, in their words. This is the whole reason the pipeline preserved verbatim quotes through four stages.
- Asks for 30 minutes. One ask.
- No adjectives about your own product. They already bought it.
- If the routing entry has no specific outcome, hold the email and say so. Do not write a generic request and do not invent a result they did not claim.
→ outputs/voc/dispatched/case-study-emails/<customer>-<date>.md
B. Landing-page copy brief
For each objection in objection-map.md:
- The objection in prospect language, with mention count and channel spread
- The page or pages it should be addressed on
- Where on the page: hero, an FAQ entry, a comparison block, a dedicated section. An objection answered in the wrong place is answered too late.
- Two or three drafted options for the copy that addresses it
- What evidence the page needs to make it credible — a number, a customer name, a screenshot
Copy constraints, applied to everything drafted here: no em dashes, no "it's not X, it's Y", no more than two consecutive negations, no robust / seamless / powerful / enterprise-grade / best-in-class / effortless / game-changing. Write the benefit first and the feature second.
→ outputs/voc/dispatched/copy-briefs/<page-slug>-<date>.md
C. PM one-pager
For each capability area in product-feedback.md:
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.
- 2mo ago First seen · 138 lines · 77 tokens per session scan A 7ae53a8ad67b
voc-dispatch is a skill published in the GitHub repository aatirar/voc-claude-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,369 once invoked, about $0.0003 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 2026-08-31.
voc-dispatch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| voc-dispatchaatirar/voc-claude-skills | Skill | 0 | 2mo ago | MIT | A | 77 | Claude Code |
| bdr-enablement-generatorStallin-Sanamandra/b2b-saas-marketing-skills | Skill | 7 | 6mo ago | MIT | A | 131 | Claude Code, Codex |
| competitive-battlecard-generatorStallin-Sanamandra/b2b-saas-marketing-skills | Skill | 7 | 6mo ago | MIT | A | 153 | Claude Code, Codex |
| marketing-ops-sop-generatorStallin-Sanamandra/b2b-saas-marketing-skills | Skill | 7 | 6mo ago | MIT | A | 160 | Claude Code, Codex |
| abm-program-orchestratorStallin-Sanamandra/b2b-saas-marketing-skills | Skill | 7 | 6mo ago | MIT | A | 148 | Claude Code, Codex |
| ceo-monthly-revenue-report-generatorStallin-Sanamandra/b2b-saas-marketing-skills | Skill | 7 | 6mo ago | MIT | A | 121 | Claude Code, Codex |
| account-research-brief-generatorStallin-Sanamandra/b2b-saas-marketing-skills | Skill | 7 | 6mo ago | MIT | A | 122 | Claude Code, Codex |