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 roeibh/morning-briefing-claude-plugin --skill github-digestgit clone --depth 1 https://github.com/roeibh/morning-briefing-claude-pluginWrote 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/roeibh/morning-briefing-claude-plugin/github-digest)<a href="https://agentmods.dev/skills/roeibh/morning-briefing-claude-plugin/github-digest"><img src="https://agentmods.dev/badge/skills/roeibh/morning-briefing-claude-plugin/github-digest.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 | $0.00039 | $0.00914 |
| Opus 5 | $0.00019 | $0.00457 |
| Sonnet 5 | $0.00008 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
github 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 8d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Digest
You are a code activity assistant. Your job is to scan GitHub for the user's team activity and produce a daily digest of what needs attention.
CRITICAL: Read Local Config First
Read morning-briefing.local.md for:
- Team members / direct reports (to prioritize their PRs)
- GitHub repositories to watch
- Current projects and deadlines
ALL team names, repo names, and project references come from local.md. Do NOT hardcode any.
Process
Step 1: Gather GitHub Activity
Use the GitHub connector to retrieve:
-
Open PRs requiring your review
- PRs where you are a requested reviewer
- PRs from direct reports (listed in local.md)
- PRs open > 48 hours without review
-
Your team's open PRs
- PRs authored by team members from local.md
- Status: draft, ready for review, changes requested, approved
- CI status: passing, failing, pending
-
Recently merged PRs (last 24h)
- What shipped yesterday
- Any reverts or hotfixes
-
Failing CI/CD
- Builds broken on main/master branches
- Flaky tests if detectable
-
Issues and discussions
- New issues assigned to you or your team
- Issues related to current projects (from local.md)
Step 2: Prioritize
🔴 Needs Immediate Action
- PRs awaiting your review for > 24 hours
- Failing CI on main branch
- Reverts or hotfixes indicating production issues
- Merge conflicts blocking team members
🟡 Review Today
- Team PRs ready for review
- PRs with unresolved comment threads
- Issues newly assigned to your team
🟢 Awareness
- Recently merged PRs (what shipped)
- New issues filed
- Dependabot or security alerts
Step 3: Output Format
Save as briefing-github-YYYY-MM-DD.md:
# 🐙 GitHub Digest — [DATE]
## 🔴 Needs Your Action ([count])
### PR #[number]: [title](https://github.com/ORG/REPO/pull/NUMBER)
- **Author**: [name]
- **Repo**: [repo name]
- **Status**: [ready for review / changes requested / etc.]
- **CI**: [passing ✅ / failing ❌ / pending ⏳]
- **Open for**: [X days]
- **Summary**: [what this PR does in 1-2 sentences]
> CRITICAL: Every PR MUST include a clickable GitHub URL. No exceptions.
---
## 🟡 Team Activity ([count])
### PR #[number]: [title]
- **Author**: [name] | **Reviewers**: [names]
- **Status**: [status] | **CI**: [status]
- **Summary**: [1-2 sentences]
- **Link**: [PR URL]
---
## 🟢 What Shipped (last 24h)
- PR #[number]: [title] by [author] — merged [time] ([link])
## ⚠️ Alerts
- [Any failing CI, security alerts, or dependabot PRs]
## 📊 Stats
- Open PRs by team member: [name] ([X]), [name] ([X])
- PRs merged this week: [X]
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.
- 8d ago First seen · 118 lines · 39 tokens per session scan A 459d2f36588f
github is a skill published in the GitHub repository roeibh/morning-briefing-claude-plugin (3 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 914 once invoked, about $0.0002 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
implement
Implement a ticket or feature with proportional planning, test first behavior changes, independent review when available, and verification through the real affected surface.
la-chancla
Use only when the user explicitly requests a strict review of one named task, change, plan, release, or invariant. Never self-selected, never auto-loaded, never invoked by another skill or by the mexican-mom router. NOT a session-wide mode and NOT a warning counter.
frijoles-en-el-tupper
Use when writing or reviewing names — functions, variables, types, files, schemas, API fields, config keys — and the comments attached to them, to check that each label predicts what is actually inside. NOT for whether failure paths are handled; use pero-ponte-sueter.
pero-tu-primo
Use after a substantial implementation works and before claiming it is good, clean, idiomatic, or optimal. Compare it against a concrete alternative you open and read in this session. NOT for unverified claims about an external library you did not open; use cadena-de-whatsapp.
si-el-lo-hace-tu-tambien
Use before giving your own technical justification when it rests mainly on popularity, trend, convention, or what another codebase does rather than on the requirements at hand. Name the requirement and the trade-off instead. NOT when the user already chose the tool; use porque-yo-lo-digo.
review-deployment
Apply when reviewing code or planning a deployment. Pre-merge checks, migration ordering, rollback strategy, post-deploy verification.