weekly

A command that reviews Git activity across several projects during a chosen time period and turns it into themed notes.

In plain words
What is it for?
Use it to create weekly work digests from Git history, optionally saving the results to a chosen notes folder.
Why use it?
It saves you from manually checking multiple repositories and remembering what you worked on. It brings fixes, refactoring, and exploration into one summary.

Command

Install

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.

agentmods
npx agentmods add commands/shdennlin/agent-plugins/weekly
Clone the repo
git clone --depth 1 https://github.com/shdennlin/agent-plugins
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00546
Opus 5 $0.00008 $0.00273
Sonnet 5 $0.00003 $0.00109
Haiku 4.5 $0.00002 $0.00055

Measured yesterday against content hash 3082dd95d2df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

weekly 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 yesterday.

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.

plugins/digest/commands/weekly.md · 65 lines

What it actually says

Weekly Digest Command

Scan git activity across multiple projects over a time window and synthesize a themed recall report — what you actually worked on, fixed, refactored, and explored.

MANDATORY FIRST STEP — DO NOT SKIP

You MUST execute this Bash command BEFORE doing anything else. The setup script parses arguments, resolves project list, validates output destination, and returns a JSON config for the agent.

"${CLAUDE_PLUGIN_ROOT}/scripts/setup-weekly.sh" $ARGUMENTS

If the script exits non-zero, report its stderr output to the user verbatim and stop. Do NOT proceed to dispatch the agent.

If --help or -h was in arguments, the script prints help to stdout and exits 0. Show that output to the user and stop.

After setup succeeds

The script's stdout is a JSON object like:

{
  "date_range": "last week",
  "projects": [{"path":"/Users/me/repo-a","name":"repo-a"}],
  "author": "[email protected]",
  "brief": false,
  "detail": false,
  "write": true,
  "out_path": "",
  "target_dir": "/Users/me/vault/Weekly"
}

Dispatch the weekly-agent with these resolved values:

Task tool:
- subagent_type: "digest:weekly-agent"
- description: "Synthesize multi-project weekly git digest"
- prompt: |
    Synthesize a themed weekly digest. The setup script has already
    resolved arguments, project paths, and output destination — your
    job is the LLM judgment work (clustering, theming, synthesis).

    Config (from setup-weekly.sh):
    <paste the JSON output from setup-weekly.sh here>

    Notes:
    - target_dir is already validated and writable; just write to it
      if write=true or out_path is set
    - Project paths are absolute; cd into each before running git log
    - If a project path is not a git repo, skip it gracefully and note
      at the end

Report the agent's output back to the user.

Changes

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.

  1. yesterday First seen · 65 lines · 16 tokens per session scan A 3082dd95d2df

Subscribe to this mod's changes

weekly is a command published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 7d ago), licensed MIT. It adds 16 tokens to every session and 546 once invoked, about $0.0001 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.