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 davekilleen/Dex --skill call-prepgit clone --depth 1 https://github.com/davekilleen/DexWrote 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/davekilleen/dex/call-prep)<a href="https://agentmods.dev/skills/davekilleen/dex/call-prep"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/call-prep/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/davekilleen/dex/call-prep"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/call-prep.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 | $0.00017 | $0.01330 |
| Opus 5.5 | $0.00007 | $0.00532 |
| Sonnet 5.5 | $0.00003 | $0.00266 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
call-prep 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Build a concise call brief from dated person, account, deal, task, and interaction evidence. Keep sourced context separate from suggested questions and unknowns.
Usage
/call-prep [person]/call-prep [company]
Evidence, authority, and recovery
Set the call brief's as-of timestamp, timezone, participant, and call time. Make
freshness relative to that as-of time. For each interaction, commitment, signal,
account field, objective, and objection, record its source path or record ID and event
date. File modified time is not an event date.
- Treat an unknown objective and unknown objection as unknown. Write
Unknown — ask; do not infer intent, buying stage, sentiment, priority, or likely objection from role, company, silence, or a generic sales pattern. - Separate sourced facts, the user's stated goals, hypotheses, and suggested questions. A useful question is not evidence that its premise is true.
- Show contradictory sources and dates side by side. Do not silently choose one.
- Never invent facts, quotes, commitments, dates, outcomes, customer counts, product capabilities, prices, ROI, payback, rollout time, or integration claims.
- Keep call prep read-only by default. A recommendation is not permission to update a person, account, deal, or task.
- Preview any requested change, require explicit confirmation from the authorized human, then read back the saved record. If a write or read-back fails, report possible partial state and stop before retrying.
Method
1. Resolve identity and call scope
Confirm the exact person/account and disambiguate duplicate names. Confirm:
- scheduled call time and timezone;
- participants and their sourced roles;
- call type only if supplied or recorded;
- the user's objective, if stated;
- the review window for prior interactions;
- authoritative sources for person, account, deal, and commitments.
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 · 174 lines · 17 tokens per session scan A 1489c951d96e
call-prep is a skill published in the GitHub repository davekilleen/Dex (515 stars, last pushed 14d ago), licensed MIT. It adds 17 tokens to every session and 1,330 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 2026-09-02.
call-prep compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| call-prepdavekilleen/Dex | Skill | 515 | 14d ago | MIT | A | 17 | Claude Code, Codex |
| nft-standardswshobson/agents | Skill | 42k | 4d ago | MIT | A | 48 | Claude Code |
| istio-traffic-managementwshobson/agents | Skill | 42k | 4d ago | MIT | A | 40 | Claude Code |
| projection-patternswshobson/agents | Skill | 42k | 4d ago | MIT | A | 36 | Claude Code |
| 9router-web-searchdecolua/9router | Skill | 32k | yesterday | MIT | A | 74 | Claude Code, Codex |
| microservices-patternswshobson/agents | Skill | 42k | 4d ago | MIT | A | 38 | Claude Code |
| track-managementwshobson/agents | Skill | 42k | 4d ago | MIT | A | 44 | Claude Code |