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 skills/jerry7991/standup-ghost/standupnpx skills add jerry7991/standup-ghost --skill standupgit clone --depth 1 https://github.com/jerry7991/standup-ghostWrote 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/jerry7991/standup-ghost/standup)<a href="https://agentmods.dev/skills/jerry7991/standup-ghost/standup"><img src="https://agentmods.dev/badge/skills/jerry7991/standup-ghost/standup.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.01092 |
| Opus 5 | $0.00044 | $0.00546 |
| Sonnet 5 | $0.00017 | $0.00218 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade A, and why
standup 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 5d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standup Ghost — the daily run
Config: ~/.config/standup-ghost/config.json. Cards: cards/ next to this plugin's root (the RUNTIME copy when invoked by the scheduler). State: ~/.local/state/standup-ghost/. Tool permissioning comes exclusively from the generated --allowedTools (headless) or interactive approval — this skill declares no tool list.
Intent (do not silently expand)
Collect → merge → compose (Yesterday/Today, bucketized) → deliver via enabled sink cards → receipts. It does NOT edit tickets, post anywhere unconfigured, summarize other people, or fabricate activity.
Step 0 — Guards
- Read config; missing ⇒ STOP: "run /standup-ghost:setup first".
state-corruptmarker set ⇒ compose but HOLD all delivery (heldpending) and say so — doctor must clear it (receipts may be incomplete; auto-delivery could double-post).pausedmarker ⇒ writeskippedreceipt (reason: paused), stop.
Step 1 — Working-day gate + window (gcal card)
Follow cards/sources/gcal.md absence detection. If today is non-working and absence.auto_skip ⇒ skipped receipt (reason: the absence type) and STOP — no pending, no alarm. Otherwise compute the window:
node <runtime>/lib/workdays.js '{"schedule_days":..., "absence_dates":[...], "min_hours":<format.lookback_hours>, "max_lookback_days":<absence.max_lookback_days>}'
lookback_hours now spans back to the last day you actually worked (weekend, leave, sick days, holidays all bridged). Heading date/day comes from running date '+%a %Y-%m-%d' — never inferred.
Step 2 — Collect (every enabled source card, degrade-per-lane)
Execute each cards/sources/*.md fetch recipe with the computed window. A dark lane = visible flag + fewer bullets; never a dead run, never invented content. Load deferred MCP tools via ToolSearch as needed.
Step 3 — Compose (format v2 — terse, bucketized)
- Merge by ticket key (branch
PROJ-42-*+ PR title + ticket = ONE item). - Two blocks only — Yesterday (outcomes) / Today (intent). One line per initiative bucket (
format.buckets_hint+ derived), maxformat.max_bullets_per_blockbucket lines; meetings without a ticket in ONE bracketed(Calls: …)line per block. Every ticket/PR is a link. No Blockers block, no tables, no sub-bullets. Reviews are ACTIVITY, not a queue: report only reviews the user actually gave (Reviews: repo#1 (approved), repo#2 (comments)) and feedback they addressed on their own PRs (addressed review feedback on repo#3— folds into that PR's bucket line). NEVER report "N PRs awaiting my review" — pending queues aren't standup content. - Heading:
format.headingwith{DOW} {DATE}fromdate,{handle}from config. - Min-content gate: fewer than
behavior.min_content_bulletsreal bullets ⇒ writeheldpending (never auto-posts) + note; STOP. - Review mode (
behavior.review_mode): deliver the draft to your own Slack DM (slack-channel card transport), writeheld, STOP. Approval =/standup-ghost:standup post.
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.
- 5d ago First seen · 47 lines · 87 tokens per session scan A 8fa0bb841ec6
standup is a skill published in the GitHub repository jerry7991/standup-ghost (2 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,092 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.
Other skills, from other repositories
remindme
⏰ simple Telegram reminders for OpenClaw. cron, zero dependencies.
collaboration-platform-administration
Administers the email, chat, meeting and file-sharing platform the organization runs on — tenant and domain configuration, mail authentication and routing, phishing and spam controls, shared mailboxes and distribution groups, external sharing and guest access, permission sprawl in file storage, and retention and legal…
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
onboarding-and-offboarding
Designs the joining and leaving experience — first-day readiness, ramp to productivity, knowledge capture, and clean exits. Use this to design or fix onboarding, shorten time to productivity, structure a leaver process, capture knowledge before someone leaves, or coordinate the access and asset steps around a joiner…
clojure-write
Guide Clojure and ClojureScript development using REPL-driven workflow, coding conventions, and best practices. Use when writing, developing, or refactoring Clojure/ClojureScript code.
mutation-testing
Run mutation testing on a Clojure namespace, generate tests to kill surviving mutations, and open draft PRs with Linear issue tracking.