weekly

A read-only weekly summary of a project's recent work and current health. It checks completed plans, active work, bugs, the highest-priority backlog items, and links between project documents.

In plain words
What is it for?
Use it for a weekly digest, a project status report, or a start-of-week review of shipped work, stale plans, open bugs, backlog priorities, and document-graph problems.
Why use it?
It gives you one concise view of what moved, what may be stuck, and what needs attention. It also points to the next action with the greatest likely benefit.

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/iwe-org/dev-workspace/weekly
Any agent
npx skills add iwe-org/dev-workspace --skill weekly
Clone the repo
git clone --depth 1 https://github.com/iwe-org/dev-workspace

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 474 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 $0.00071 $0.00474
Opus 5 $0.00036 $0.00237
Sonnet 5 $0.00014 $0.00095
Haiku 4.5 $0.00007 $0.00047

Measured 2d ago against content hash 80ea11798bed, 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 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/weekly/SKILL.md · 37 lines

What it actually says

Weekly digest

A read-only sweep of the graph that answers: what moved, what's stuck, what's next. Numbers come from frontmatter and git — never from memory.

Steps

  1. Shipped. Plans completed in the last 7 days: iwe find --filter '{stage: done}' --included-by data/plans -f json and keep those with a completed date in range; cross-check with git log --since '7 days ago' --oneline. List releases cut, if any.
  2. In flight. Active plans (no stage) under ## Active in data/plans.md; flag any untouched for 14+ days (last commit touching the file) as possibly stalled or silently done.
  3. Open bugs. Docs under data/bugs.md without stage: done/cancelled.
  4. Backlog head. ## High items in data/backlog.md, plus how long they've sat (created).
  5. Graph health. iwe schema validate (report violations) and iwe stats (dangling links, plus any data/ document listed under Orphans other than data/index — every content doc should be reachable from a hub). Healthy means zero of each.
  6. Print the digest — shipped / in flight / bugs / backlog / health — and end with the single most leveraged next action, chosen from what the sweep showed, with a one-line justification.

Rules

  • Read-only: this skill writes no files and changes no statuses; if the sweep finds inconsistencies (a done plan still under Active), report them as the next action instead of fixing silently.
  • Every number in the digest traces to a query or git — no estimates.
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 · 37 lines · 71 tokens per session scan A 80ea11798bed

Subscribe to this mod's changes

weekly is a skill published in the GitHub repository iwe-org/dev-workspace (5 stars, last pushed 23d ago), licensed MIT. It adds 71 tokens to every session and 474 once invoked, about $0.0004 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.