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 Kevin-Liu-01/Agent-Machines --skill project-briefinggit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/project-briefing)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/project-briefing"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/project-briefing/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/kevin-liu-01/agent-machines/project-briefing"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/project-briefing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00593 |
| Opus 5 | $0.00029 | $0.00296 |
| Sonnet 5 | $0.00012 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
project-briefing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Briefing
Overview
Produce a rich Markdown executive briefing of the last 24 hours of commits touching the current working directory (or a specified directory). Group changes by workstream, not by individual commit.
Workflow
1) Fetch latest from remote
git fetch origin
Determine the default branch (origin/main or origin/master).
2) Gather commits
git log --since="24 hours ago" --format='%H %an <%ae> %s' origin/<default-branch>
For each commit, also get the stat and body:
git show --stat --format='%an%n%s%n%b' <hash>
Only include commits that touch files within the current working directory (or specified directory scope).
3) Enrich with PR data
Use gh to fetch PR information when available:
gh pr list --state merged --search "merged:>=$(date -v-24H +%Y-%m-%d)" --json number,title,body,url,author,reviews,comments
Include PR links inline as [#123](url) without a "PRs:" label. Pull in review comments if they add useful context.
4) Group by workstream
Analyze the commits and PRs to identify logical workstreams (e.g., "Rendering Engine Refactor," "New Tower Implementation," "UI Polish"). Group related changes together even if they span multiple commits or PRs.
5) Format the briefing
Use this structure:
Here's the last 24h brief for <directory>:
*Narrative walkthrough with owners; grouped by workstream.*
---
# <Workstream Title>
<Short narrative explaining the changes in plain language.>
- **Author Name** did X, Y, Z [#PR](url)
- **Author Name** followed up with A, B [#PR](url)
---
# <Next Workstream Title>
...
Formatting rules:
- H1 for workstream sections
- Italics for the subtitle
- Horizontal rules between sections
- Bold author names in bullet points
- PR links inline
- No commit hashes
- No "Key commits" section
- No per-commit bullet lists (group by workstream narrative)
- Bullets and bolding for readability
Content rules:
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 · 92 lines · 58 tokens per session scan A 465fb87e7043
project-briefing is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 593 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
gh-issues
Triage GitHub issues, select safe candidates, implement focused fixes, open pull requests, and address actionable review feedback.
github
Use GitHub CLI for repositories, issues, pull requests, reviews, CI runs, releases, and structured GitHub API queries.
oss-workflow
Open-source project success workflow for viznoir. Codifies contributor onboarding, release management (Release Please + PyPI), issue triage, and showcase curation. Triggers: release, contributor, onboarding, PyPI publish, issue triage, showcase, CHANGELOG, good first issue.
status
Generate a status report across all workstreams using git history and GitHub issues. Shows active work, recent changes, and open PRs.
handoff-resume
Resume in-progress coding work across sessions from a HANDOFF.md and a dirty git working tree. Use when a task says "continue from HANDOFF.md", "retomar o processamento", or when picking up a repo mid-change with uncommitted edits and an open PR. Covers reading continuity docs, reconciling the real tree, decoding repo…
github-issue-to-pr
Carry a GitHub issue to a verified PR with honest CI state.