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 jamestorrevillas/dev-skills --skill technical-communicationgit clone --depth 1 https://github.com/jamestorrevillas/dev-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/jamestorrevillas/dev-skills/technical-communication)<a href="https://agentmods.dev/skills/jamestorrevillas/dev-skills/technical-communication"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/technical-communication.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 5.1 | $0.00069 | $0.00629 |
| Opus 5 | $0.00034 | $0.00315 |
| Sonnet 5 | $0.00014 | $0.00126 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
technical-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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Communication
The Core Problem
Technical people communicate for accuracy. Non-technical people communicate for decisions. These are different goals requiring different approaches.
Rule: Lead with impact, follow with mechanism. Never the reverse.
Audience-First Framework
Before writing or speaking, answer:
- Who is the audience? (developer, PM, executive, client)
- What decision do they need to make?
- What do they already know?
- What do they care about? (reliability, cost, speed, risk)
Then adapt every word to those answers.
Explaining Technical Concepts
The Analogy Method
Find a familiar concept that shares the same structure:
Cache → A sticky note on your desk vs going to the filing cabinet
API → A restaurant menu — you order, the kitchen delivers, you don't see the kitchen
Microservices → A food court vs a single restaurant kitchen
The Why-Before-What Pattern
WRONG: "We need to implement Redis caching."
RIGHT: "Our API is responding slowly under load.
Caching the most frequent DB queries in Redis
would cut response time by ~70% at minimal cost."
Always lead with the problem and impact, then the solution.
Writing for Different Audiences
For Executives
- One paragraph max per topic
- Lead with business impact (cost, risk, user experience)
- No acronyms without expansion
- Include a clear recommendation
For Product Managers
- Connect every technical decision to user or product impact
- Flag trade-offs that affect timeline or scope
- Be clear about what you need from them (decision, info, approval)
For Other Developers
- Be precise and specific
- Include relevant context (why, not just what)
- Reference code, docs, or tickets directly
The BLUF Format (Bottom Line Up Front)
For all written technical communication:
[One sentence: what you want them to know or do]
[2-3 sentences: context and reasoning]
[Optional: details, alternatives, risks for those who want depth]
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.
- 7d ago First seen · 95 lines · 0 tokens per session scan A 47a35dd0c4cc
technical-communication is a skill published in the GitHub repository jamestorrevillas/dev-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 629 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.
Other skills, from other repositories
coaching-techniques
GROW model, active listening, developmental feedback, and team growth approaches.
counseling-psychology
Therapeutic frameworks, assessment, ethical practice, and client documentation for counselors and psychologists.
cognitive-load
Don't overwhelm — chunk, scaffold, summarize first.
learning-psychology
Help humans learn through partnership, not instruction.
onboard
Walk a new teammate through the team's curated agent toolchain.
learn
Learn and understand a concept in depth. Args.