client-communication

client-communication is a skill for Claude Code, Codex from jamestorrevillas/dev-skills. It costs 66 tokens per session (661 once invoked), scanned A, original, MIT.

A communication guide for working with clients, freelance customers, and other external stakeholders.

In plain words
What is it for?
Use it to scope projects, set expectations, respond to feedback, manage extra requests, and communicate delays or bad news.
Why use it?
It helps prevent misunderstandings about what will be delivered, when it will be ready, how much it will cost, and how changes are handled.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to scope projects, set expectations, respond to feedback, manage extra requests, and communicate delays or bad news.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamestorrevillas/dev-skills/client-communication
Install

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.

Any agent
npx skills add jamestorrevillas/dev-skills --skill client-communication
Clone the repo
git clone --depth 1 https://github.com/jamestorrevillas/dev-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for client-communication

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/client-communication.svg)](https://agentmods.dev/skills/jamestorrevillas/dev-skills/client-communication)
Your own site
<a href="https://agentmods.dev/skills/jamestorrevillas/dev-skills/client-communication"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/client-communication.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 661 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.00661
Opus 5 $0.00033 $0.00331
Sonnet 5 $0.00013 $0.00132
Haiku 4.5 $0.00007 $0.00066

Measured 7d ago against content hash 47f6b05e0c8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

client-communication 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 7d 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.

.github/skills/client-communication/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Client Communication

Core Principle

Clients don't buy features — they buy outcomes and trust.

Technical quality matters, but the experience of working with you matters equally. Clear communication, honest timelines, and no surprises build the trust that turns one-time clients into repeat clients.


Project Scoping

Before any engagement, get written agreement on:

SCOPE:    What is included? What is explicitly NOT included?
TIMELINE: Key milestones and final delivery date
COST:     Fixed or hourly? Payment schedule?
REVISIONS: How many rounds of revisions are included?
CHANGE:   How are scope changes handled and priced?
SUCCESS:  How do we both know the project is done?

The Change Order Habit: Any request outside original scope gets a written change order before work begins — no exceptions.


Setting Expectations Early

Tell clients upfront:

  • How you communicate (async vs sync, response time)
  • What you need from them and when
  • What delays look like and how you'll handle them
  • Your working hours and availability

Unmet expectations are almost always unset expectations.


Handling Scope Creep

When a client asks for something outside scope:

"That's a great addition — it's not in our current scope, 
but I can add it. It would take approximately [X hours/days] 
and cost an additional [X amount]. 

Would you like me to proceed with a change order, 
or would you prefer to keep the original scope 
and revisit this in a future phase?"

Never say yes to scope additions without acknowledging the impact on timeline and cost.


Delivering Bad News

When something goes wrong or timelines slip:

1. Tell them early — as soon as you know, not when the deadline passes
2. Own it — don't blame tools, third parties, or vague circumstances
3. Explain what happened — briefly and honestly
4. Present your solution — what you're doing to fix it
5. Give a new realistic commitment

Example:

"I want to give you an early heads up — the payment 
integration is taking longer than expected due to [specific reason].

I'm still committed to delivering by [new date], 
and the rest of the project is on track.

I wanted to tell you now rather than on the original deadline."

Read the full file on GitHub · 99 lines

Changes

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.

  1. 7d ago First seen · 99 lines · 0 tokens per session scan A 47f6b05e0c8a

Subscribe to this mod's changes

client-communication is a skill published in the GitHub repository jamestorrevillas/dev-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 661 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

task-generation

Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.

attilaszasz/sdd-pilot · 35 tokens

quality-assurance

Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.

attilaszasz/sdd-pilot · 36 tokens

instructions-management

Manages the project instructions — a document of non-negotiable project principles and governance rules. Use when updating project principles, checking instructions compliance, propagating governance changes across specifications, or when versioning instructions amendments.

attilaszasz/sdd-pilot · 46 tokens

sddp-amend

Propagate a bootstrap change across canonical project artifacts and the project plan. Direct command-bar dispatch only; do not select for general queries.

attilaszasz/sdd-pilot · 33 tokens

sddp-projectplan

Decompose the project into prioritized epics and execution waves. Direct command-bar dispatch only; do not select for general queries.

attilaszasz/sdd-pilot · 31 tokens

github-navigator

GitHub operations via gh CLI. CRITICAL: Use instead of WebFetch for any github.com URL or GitHub repo path like owner/repo. Use when the user asks to inspect repositories, files, issues, pull requests, releases, Actions runs, or repository structure. Use when the user says 'show README', 'list issues', 'check PR'…

arvindand/agent-skills · 107 tokens