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 dailyaiagents-cpu/dailyai-os --skill state-of-company-publishergit clone --depth 1 https://github.com/dailyaiagents-cpu/dailyai-osWrote 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/dailyaiagents-cpu/dailyai-os/state-of-company-publisher)<a href="https://agentmods.dev/skills/dailyaiagents-cpu/dailyai-os/state-of-company-publisher"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/state-of-company-publisher/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/dailyaiagents-cpu/dailyai-os/state-of-company-publisher"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/state-of-company-publisher.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 | $0.00115 | $0.00899 |
| Opus 5 | $0.00057 | $0.00449 |
| Sonnet 5 | $0.00023 | $0.00180 |
| Haiku 4.5 | $0.00012 | $0.00090 |
Grade A, and why
state-of-company-publisher 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
state-of-company-publisher
The thesis: a weekly narrative of the company's substrate, gates, and testing-cadence is more credible than a marketing page. Cooper writes the private sunday-review; this skill composes the public counterpart, scrubbed of MRR, customer counts, and lead names — surface only the architecture and the methodology.
The output replaces last week's site/state.html; one canonical URL.
Procedure
bash skills/state-of-company-publisher/run.sh # full publish
bash skills/state-of-company-publisher/run.sh --dry-run # build + gate, no write
Pipeline
- Inputs (read-only, private):
- Open handoff counts by specialist (no titles):
data/team_bus/handoffs/open/* - Latest sunday-review (if exists):
data/founder-reviews/<latest>.md— extract a 200-word public-safe summary - Recent decisions:
data/decisions/cont-*-*.mdlast 7 days, summarize each with title + 1-sentence outcome - Recent P-gate catches: grep
data/decisions/*.mdfor "P-gates triggered"
- Open handoff counts by specialist (no titles):
- Voice anchor: VOICE.md sentence rules + last 2 founder-letter drafts.
- Local Ollama call (qwen3.5:latest, think=false, ~1500 num_predict):
- System prompt: VOICE.md + "weekly state of the company" framing
- Constraints: ≥3 sections (shipped, caught, testing), no MRR, no customers, no lead names, no auth tokens, no API keys
- Voice-gate (newsletter surface, threshold 70 hard).
- Scrubber HARD on the assembled narrative.
- If both pass →
site/state.html(replaces last week's). If either fails →data/state-drafts/<YYYY-MM-DD>.mdfor Cooper.
Status codes
STATUS=ok html=<path> score=<N> /
STATUS=draft path=<draft> reason=<voice-fail|scrubber-fail> score=<N> /
STATUS=skip reason=<...> / STATUS=error reason=<...>
Output schema (public site/state.html)
Static-template HTML wrapping a markdown body that contains:
# State of the company — week of <YYYY-MM-DD>
## What we shipped this week
3-5 bullets, each one specific commit/decision.
## What we caught this week
3-5 bullets, each one specific gate or P-fire that prevented broken work
from shipping. (P-gates as an artifact, not the bugs themselves.)
## What we're testing next
2-4 bullets, each one a specific experiment with a falsifier.
---
_Auto-published by state-of-company-publisher. Voice-gate <score>/100,
scrubber clean. Source markdown: data/state-published/<YYYY-MM-DD>.md._
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 87 lines · 115 tokens per session scan A db74e9c9162d
state-of-company-publisher is a skill published in the GitHub repository dailyaiagents-cpu/dailyai-os (0 stars, last pushed 4mo ago), licensed MIT. It adds 115 tokens to every session and 899 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…