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 agentmods add commands/shdennlin/agent-plugins/weeklygit clone --depth 1 https://github.com/shdennlin/agent-pluginsWhat 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 | $0.00016 | $0.00546 |
| Opus 5 | $0.00008 | $0.00273 |
| Sonnet 5 | $0.00003 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
weekly scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Weekly Digest Command
Scan git activity across multiple projects over a time window and synthesize a themed recall report — what you actually worked on, fixed, refactored, and explored.
MANDATORY FIRST STEP — DO NOT SKIP
You MUST execute this Bash command BEFORE doing anything else. The setup script parses arguments, resolves project list, validates output destination, and returns a JSON config for the agent.
"${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.
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.
- yesterday First seen · 65 lines · 16 tokens per session scan A 3082dd95d2df
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.