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 jasonm4130/claude-skills --skill morninggit clone --depth 1 https://github.com/jasonm4130/claude-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/jasonm4130/claude-skills/morning)<a href="https://agentmods.dev/skills/jasonm4130/claude-skills/morning"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/morning/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/jasonm4130/claude-skills/morning"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/morning.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 | $0.00138 | $0.01091 |
| Opus 5 | $0.00069 | $0.00545 |
| Sonnet 5 | $0.00028 | $0.00218 |
| Haiku 4.5 | $0.00014 | $0.00109 |
Grade A, and why
morning 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 6d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage the night
The loop leaves its evidence in three places and remembers nothing else. Read all three before saying anything. Announce: "Using nightshift:morning to read last night's run."
1. Gather
cfg=loop/config; . $cfg 2>/dev/null
journal=~/.local/state/nightshift/$(basename "$PWD")/journal.md
- Journal: everything after the last
start:line. EachSTOP:line names why the night ended;task N:lines carry cost and round outcomes. - Pull requests:
gh pr list --label land --state open --json number,title,isDraft,labels,urland the same for--label land:blocked. A draft with the blocked label is a task that failed its repair round; its body has the generator's report, the skeptic's verdict and the verifier's tail. Merged PRs since the start line:gh pr list --label land --state merged --search "merged:>=<date>". - Run directory:
~/.local/state/nightshift/<repo>/<date>-t<N>/holdsbrief.md,gen-<round>.md,skeptic-<round>.md,check-<round>.logand the JSON envelopes. Read the log tail and the skeptic before judging. - The switch:
gh variable get LANDING_STATE. The loop flips nothing; if it is notrun, a human froze it or never armed it.
2. Report, one block per stop
Headline first, then the consequence, then the fix. No raw log pastes; quote the one line that matters.
- Landed. "Task 3 landed as #41, 2 rounds, $5.10." Nothing to do; say it.
- Blocked (
land:blockeddraft). Say which of the three refused it: verifier red (quote theERROR <step>line), skepticREFUTED(quote its reason), or the generator'sBLOCKED:line. The consequence is that every later task waits, because the loop stops at the first blocked task. - Waiting (open non-draft PR). CI is still running, or a check never
registered (wait mode with a wrong
EXPECTED_CHECKSname); the merge script's output is in the journal. - Closed without merging. A human decided; the loop will not retry until the PR is reopened or the task is removed from the plan.
- Produced nothing. The generator made no commits; the brief was probably not self-contained. The fix is a plan edit, not a retry.
- Frozen / deadline / MAX. The night ended on purpose; say which.
- No
start:line today. launchd did not fire:launchctl list | grep nightshift, and thestdout/stderrpaths inloop/launchd.plist.
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.
- 6d ago First seen · 73 lines · 138 tokens per session scan A eb97be404cae
morning is a skill published in the GitHub repository jasonm4130/claude-skills (5 stars, last pushed 5d ago), licensed MIT. It adds 138 tokens to every session and 1,091 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
pr-create
Creates a pull request from current changes, monitors GitHub CI, and debugs any failures until CI passes. Activate when the user says "create pr", "make a pr", "open pull request", "submit pr", "pr for these changes", or wants to get their current work into a reviewable PR. Assumes the project uses git, is hosted on…
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.