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 ship-log-draftgit 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/ship-log-draft)<a href="https://agentmods.dev/skills/dailyaiagents-cpu/dailyai-os/ship-log-draft"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/ship-log-draft/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/ship-log-draft"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/ship-log-draft.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 | $0.00098 | $0.00765 |
| Opus 5 | $0.00049 | $0.00382 |
| Sonnet 5 | $0.00020 | $0.00153 |
| Haiku 4.5 | $0.00010 | $0.00076 |
Grade A, and why
ship-log-draft scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ship-log-draft
Why this exists
VISION.md / Phase F.2: "qualitative weekly receipts." The Friday ship log is the public artifact that proves the system shipped this week. Not "$N MRR" or "X customers" — what actually shipped, what broke, what was learned. Anyone who reads /log/ for 4 weeks understands how the system thinks.
Procedure
bash ${OPENCLAW_HOME}/skills/ship-log-draft/run.sh
SHIP_LOG_DRYRUN=1 → write the draft, run gates, but skip the Telegram notification.
The draft has 5 sections:
- Shipped —
git log --since='7 days ago' --no-merges, top 15 commits - Skills auto-promoted —
~/.hermes/skills/auto/directories created in last 7 days - What broke (and the fix) —
data/postmortems/*.mdmtimed in last 7 days, top 3 - What I learned — Cooper-only placeholder; 100-200 words; the one mental-model update that shaped the week
- What's next —
data/improvement-queue/approved/*.mdtop 3
The gate flow
- Draft written to
data/ship-log/<date>-draft.md - Voice-gate runs immediately (advisory — score < 70 warns, doesn't block)
- Scrubber runs immediately (advisory at draft stage; HARD gate at publish)
- Cooper sees the Telegram, edits the "What I learned" section + any flagged commit-message lines
- Cooper runs
ship-log-publish <date>which re-runs both gates HARD
The draft stage is intermediate. Commit messages legitimately reference financial terms ("Stripe MCP + live MRR in /dashboard" describes architecture, not P&L). The scrubber flags them at draft so Cooper can rewrite them before publish.
Hard rules
- Cooper writes "What I learned". Never auto-generated. The placeholder text contains a sentinel string that ship-log-publish detects and blocks on.
- Scrubber HARD-gates publish, not draft. Drafts may contain financial terms in commit-message context; publish requires clean.
- No financial figures fabricated. The draft surfaces real commit messages verbatim; if a commit message accidentally includes a dollar amount, the publish-time scrubber catches it.
- 5-section structure preserved. Cooper edits "What I learned"; the other 4 sections are auto-aggregated.
What ships with it
1 file 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.
- 10d ago First seen · 60 lines · 98 tokens per session scan A fb42076c4f36
ship-log-draft is a skill published in the GitHub repository dailyaiagents-cpu/dailyai-os (0 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 765 once invoked, about $0.0005 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
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.