aw-daily

An unattended daily workflow for the aw-author plugin. It researches information, compares findings with project files, creates GitHub issues, implements changes on a development branch, and can open, review, and merge a pull request.

In plain words
What is it for?
Use it for daily intelligence reports, ecosystem monitoring, gap analysis, issue creation, development-branch changes, and pull requests.
Why use it?
It combines recurring research and implementation steps into one scheduled process. Options let you run only selected phases, such as a dry run or research without code changes.

Skill for Claude CodeCodex

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 skills/zircote-plugins/github-agentic-workflows/aw-daily
Any agent
npx skills add zircote-plugins/github-agentic-workflows --skill aw-daily
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/github-agentic-workflows

Made for: Claude Code, Codex.

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,220 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 $0.00094 $0.03220
Opus 5 $0.00047 $0.01610
Sonnet 5 $0.00019 $0.00644
Haiku 4.5 $0.00009 $0.00322

Measured 2d ago against content hash 8a0f14f493ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aw-daily 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 2d 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.

.claude/skills/aw-daily/SKILL.md · 375 lines

How it starts

The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Daily Intelligence Pipeline

You are an autonomous operations agent. Execute all phases below in order. If any phase fails, follow the error mode specified. Do not prompt the user for input at any point. This pipeline is designed for fully unattended execution.

Parse the argument string for optional flags:

  • --dry-run -- Research + gap analysis only, show diff, do not commit or PR
  • --skip-research -- Start at Phase 4 using the latest report in outputs/gh-aw-reports/
  • --skip-implementation -- Research + gap analysis + issues only, do not edit files or PR
  • --no-merge -- Create PR but do not auto-merge to develop

Phase 0: Pre-flight & Idempotency

  1. Determine today's date: date +%Y-%m-%d -> store as TODAY
  2. Verify gh CLI: gh auth status
  3. Verify clean working tree: git status --porcelain must be empty
    • If dirty: ABORT -- "Working tree is dirty. Commit or stash before running /aw-daily."
  4. Capture current branch: git branch --show-current -> store as ORIGINAL_BRANCH

Ensure develop branch exists:

if ! git ls-remote --exit-code origin develop >/dev/null 2>&1; then
  git checkout main
  git checkout -b develop
  git push -u origin develop
  git checkout "$ORIGINAL_BRANCH"
fi
git fetch origin develop

Idempotency checks:

  1. Check if today's Discussion already exists:
EXISTING_DISCUSSION=$(gh api graphql -f query='{ repository(owner:"zircote", name:"github-agentic-workflows") { discussions(categoryId:"DIC_kwDORSXBr84C61Lr", first:5, orderBy:{field:CREATED_AT, direction:DESC}) { nodes { title url } } } }' -q ".data.repository.discussions.nodes[] | select(.title | contains(\"$TODAY\")) | .url")

If found and --skip-research not set: set RESEARCH_DONE=true, store URL as DISCUSSION_URL

  1. Check if today's PR already exists:
EXISTING_PR=$(gh pr list --repo zircote/github-agentic-workflows --base develop --search "daily-intelligence-$TODAY" --state all --json number,url -q '.[0].url')

If found: report "Today's pipeline already completed. PR: $EXISTING_PR" and exit successfully.

Read the full file on GitHub · 375 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 375 lines · 94 tokens per session scan A 8a0f14f493ad

Subscribe to this mod's changes

aw-daily is a skill published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 3,220 once invoked, about $0.0005 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.