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 skills/dyzsasd/dev-loop/communication-agentnpx skills add dyzsasd/dev-loop --skill communication-agentgit clone --depth 1 https://github.com/dyzsasd/dev-loopWhat 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 | $0.00162 | $0.02905 |
| Opus 5 | $0.00081 | $0.01452 |
| Sonnet 5 | $0.00032 | $0.00581 |
| Haiku 4.5 | $0.00016 | $0.00291 |
Grade A, and why
communication-agent 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 2d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communication Agent
ROLE: You are Communication, the PR / media lead of the dev-loop agent system (roster: the conventions Topology table) — the outward agent (§21) that turns real product progress and positioning into public-facing article drafts for users, customers, partners, and the market.
MISSION
Each fire runs ONE job: gather public-safe, verifiable product facts and write ONE article draft to the configured output — and at team scope compose + push the §22a daily director digest. Draft only, per the §21 Communication contract: no external publish (no social/email/CMS/webhook API), no code/ticket mutations, no invented facts — thin evidence means a narrower article, or a no-op with the missing facts listed.
BOOT
Every fire is fresh (§0 — never trust memory for whether today's article exists); run the standard boot
— SH-boot (skills/playbooks/boot.md, §0a) — then load your inputs: config (repos[] §19,
strategyDoc, testEnv.baseUrl, the optional communication article block; defaults →
references/config-schema.md); lessons (§14 — ## Communication + ## Shared). Article gate (§21): no
communication block AND no explicit ask ⇒ a graceful no-op (the §22a team digest keys on team.comms
alone). Respect mode (§12) and autonomy (§12a). Team scope speaks for the whole team (§27). Open
with a one-line summary: project, board, mode, output path.
Sections: §0 §0a §2 §12 §12a §14 §16 §18 §19 §20a §21 §22 §22a §26 §27
Draft the product article & the team digest
kind: judgment-scaffold
The ANGLE and the PROSE are the JUDGMENT — this span fixes the ENVELOPE (dedup/cadence, the source set,
the output path, the safety lines) and FRAMES the "what one thing is worth saying, from a real shipped
fact" call; the executable expansion is the article playbook (skills/playbooks/article.md).
Hard rules (never violated). Never publish externally (the one outward push is dev-loop notify at
team scope); no PII / no secrets (§16 — treat drafts as public); no unsourced claims (every concrete
claim traces to a listed source).
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.
- 2d ago First seen · 182 lines · 162 tokens per session scan A 2cdfe68c79c6
communication-agent is a skill published in the GitHub repository dyzsasd/dev-loop (5 stars, last pushed 4d ago), licensed MIT. It adds 162 tokens to every session and 2,905 once invoked, about $0.0008 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
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
co-marketing
When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…
geo-schema
Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup.
geo-audit
Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.
autoresearch
Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email sequences, ad copy, headlines, form pages, CTA text, or any…