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 mostafa-drz/claude-skills --skill project-updatesgit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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/mostafa-drz/claude-skills/project-updates)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/project-updates"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/project-updates/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/mostafa-drz/claude-skills/project-updates"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/project-updates.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 | $0.00122 | $0.04069 |
| Opus 5.5 | $0.00049 | $0.01628 |
| Sonnet 5.5 | $0.00024 | $0.00814 |
| Haiku 4.5 | $0.00012 | $0.00407 |
Grade A, and why
project-updates 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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Updates
Draft Linear project status updates — one per project, in the team template (Done / In Progress / Next / Blockers) — from everything I did today, across every tool I use. Show drafts, capture edits, learn patterns.
Preferences
On startup, use the Read tool on ~/.claude/skills/project-updates/preferences.md. If not found, no preferences are set.
Learnings
On startup, use the Read tool on ~/.claude/skills/project-updates/learnings.md. If not found, treat as empty. These are accumulated patterns from past edits — apply them silently when drafting. Do not mention the learnings file to the user unless adding to it.
Context
On startup, use Bash to gather (skip any that fail):
- Current date:
date +%Y-%m-%d - Git user email:
git config --global user.email - GitHub username:
gh api user -q .login 2>/dev/null - Linear user (from MCP):
mcp__claude_ai_Linear__get_userwith self
Command routing
Check $ARGUMENTS:
help→ display help, stopconfig→ interactive setup, stopreset→ deletepreferences.md(keep learnings and drafts), confirm, stopforget-learnings→ deletelearnings.md, confirm, stopshow-learnings→ printlearnings.mdcontents, stop- anything else (including empty) → run the skill
Flags
Parse from $ARGUMENTS:
--since <time>— lookback window (e.g.,24h,48h,yesterday,monday). Default: from preferences, else24h.--projects <list>— comma-separated Linear project slugs/names to include (overrides default set).--project <slug>— shortcut for a single project.--sources <list>— comma-separated:linear,git,github,slack,notion,gmail,calendar. Default: all available.--dry-run— draft only; skip writing todrafts/and skip learnings capture.--no-feedback— skip the per-draft feedback prompt.--format <style>—template(default: Done/In Progress/Next/Blockers) ornarrative(paragraph style).
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 Changed · +3 lines · +122 tokens per session 15fb3093f799
- 1mo ago First seen · 381 lines · 0 tokens per session scan A 2eba319465ff
project-updates is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 4,069 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
wrap-up
Saves today's work session as a four-line entry (did, decided, open, next) at the top of the project's log.md, after the student confirms it, so a fresh chat can continue tomorrow with /pick-up. Writes to projects/ /log.md or career-vault/log.md, one entry per project touched, never to new-client. Use when the student…
pick-up
Reads the newest entry of a project's log.md and tells the student where they left off: what they did and decided, what is open, and the next step. Takes an optional project name. With several projects and no name, shows a menu of each project's last entry. Read only. Use when the student says pick up, where did I…
scrum-master-agent
Comprehensive Scrum Master assistant for sprint planning, backlog grooming, retrospectives, capacity planning, and daily standups with intelligent context-aware reporting.
shipkit-user-instructions
Use when there are manual tasks the user must complete. Triggers: 'create task', 'track TODO', 'user needs to', 'manual step required'.
codex-symphony
Install and operate a portable OpenAI Symphony + Linear orchestration setup in any Git repository. Use when the user wants a one-command local Symphony runner, a reusable WORKFLOW template, background launch scripts, or a Codex wrapper that restarts Symphony automatically when reopening the CLI.
shipkit-orchestrate
Core automation engine. Drives a set of steps to a confirmed ground-truth bar via a main-session delegate → reconcile → re-dispatch loop. Phase skills (build, review, direction) call it; can also run directly. Two modes: autonomous (run to done unattended) and steered (coordinate, surface to user). Triggers: invoked…