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 | $0.00005 | $0.04015 |
| Opus 5 | $0.00003 | $0.02008 |
| Sonnet 5 | $0.00001 | $0.00803 |
| Haiku 4.5 | $0.00001 | $0.00402 |
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 10d 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 — 381 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.
- 10d 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 27d ago), licensed MIT. It adds 5 tokens to every session and 4,015 once invoked, about $0.0000 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 skills, from other repositories
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.
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
daily-working
End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…
shipkit-user-instructions
Use when there are manual tasks the user must complete. Triggers: 'create task', 'track TODO', 'user needs to', 'manual step required'.
caregiver-coordination
Analyze caregiver coordination platforms for scheduling optimization, task assignment, handoff communication, family/professional caregiver integration, care plan compliance, burnout prevention, and documentation workflows..
grant-writer
Audit a grant management system for proposal workflow efficiency, deadline tracking, budget-narrative alignment, outcome reporting, compliance readiness, and win rate optimization. Use when reviewing nonprofit grant software, building a grants CRM, analyzing proposal pipelines, or evaluating funder reporting tools.