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 fredoliveira/agents --skill weekly-reviewgit clone --depth 1 https://github.com/fredoliveira/agentsWrote 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/fredoliveira/agents/weekly-review)<a href="https://agentmods.dev/skills/fredoliveira/agents/weekly-review"><img src="https://agentmods.dev/badge/skills/fredoliveira/agents/weekly-review/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/fredoliveira/agents/weekly-review"><img src="https://agentmods.dev/badge/skills/fredoliveira/agents/weekly-review.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 | $0.00036 | $0.00896 |
| Opus 5.5 | $0.00014 | $0.00358 |
| Sonnet 5.5 | $0.00007 | $0.00179 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
weekly-review 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Review
Purpose
Process a calendar week's daily notes to generate a summary that captures key insights, tracks action items, and identifies ideas worth developing into atomic notes. The summary is written into the ## Review section of that week's weekly note.
Instructions
1. Determine the target week
- Default to the last completed week (Monday–Sunday). If the user names a specific week or date, use that instead.
- Compute the weekly note name in
gggg-[W]wwformat. Use the shell to stay accurate:- Last completed week:
date -v-7d -v-mon +%G-W%V(e.g.2026-W24) - Current week:
date +%G-W%V
- Last completed week:
- The weekly note lives at
Weekly/<gggg-[W]ww>.md(e.g.Weekly/2026-W24.md). - Compute the Monday–Sunday date range for that week (e.g.
date -v-7d -v-mon +%Y-%m-%dfor the Monday, then add days).
2. Locate and read the week's daily notes
- Find daily notes in
Daily/YYYY/MM-Month/YYYY-MM-DD.mdformat for each of the 7 days. - Read each note that exists, in chronological order. Skip days with no note.
3. Extract and summarize
For each daily note, identify:
| Category | What to look for |
|---|---|
| Key findings | Insights, learnings, realizations, decisions made |
| Relevant links | URLs, references, resources worth revisiting |
| Action items | Tasks mentioned, TODOs, follow-ups needed |
4. Identify emergent topics
Look for recurring themes or ideas that appeared multiple times across the week. These are candidates for atomic notes.
Signs of an emergent topic:
- Mentioned in more than one of the daily notes
- An insight that surprised or shifted thinking
- A connection between previously unrelated ideas
- Something worth remembering long-term
5. Write the review into the weekly note
The weekly note's ## Review section already contains three empty subsections (created from the template):
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.
- 1mo ago First seen · 82 lines · 36 tokens per session scan A 34d289a5c4b9
weekly-review is a skill published in the GitHub repository fredoliveira/agents (25 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 896 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
todays-focus
Choose three meaningful focus areas for today using current tools and personal vault context, with a check-in, three journal prompts, and optional saving of the full reflection.
close-day
Review today's log and meeting notes, optionally import Granola meetings, propose Atomic Notes, and suggest next-day actions.
shell-env
Edit the Stow-managed shell and terminal environment in /.dotfiles/home, including zsh, aliases, tmux/sesh, Starship, Ghostty, yabai, Git, and link structure. Use for focused terminal configuration changes. Route Neovim work to neovim and whole-system health checks to audit.
til
Save demonstrated learning, corrected misconceptions, and useful examples from a session as a durable Obsidian TIL note. Use when a learning workflow hands off a session or the user asks to save what they learned.
standup
Draft a concise daily standup from Git evidence and user-provided non-code work. Use for standups, daily updates, or summaries of the requested work period.
tfw-daily-task
Complete a bounded everyday request after project and purpose checks, preserving selected Trace and a checked result without a second planning approval.