recap

recap is a skill for Claude Code, Codex from jerry7991/standup-ghost. It costs 84 tokens per session (715 once invoked), scanned A, original, MIT.

A search and summary tool for your archived daily work updates. It can summarize a period or find mentions of a topic, and can also produce a read-only team summary from a shared archive.

In plain words
What is it for?
Use it to recap a week, month, sprint, or custom date range, find when a project or ticket was discussed, or summarize teammates' posted updates.
Why use it?
It removes the need to open many dated update files when reconstructing what happened. It searches stored history without adding new records or automatically posting anything.

Skill for Claude CodeCodex

Part of the standup-ghost plugin — 4 skills shipped together

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/jerry7991/standup-ghost/recap
Any agent
npx skills add jerry7991/standup-ghost --skill recap
Clone the repo
git clone --depth 1 https://github.com/jerry7991/standup-ghost

Made for: Claude Code, Codex.

Or install standup-ghost, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for recap

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerry7991/standup-ghost/recap.svg)](https://agentmods.dev/skills/jerry7991/standup-ghost/recap)
Your own site
<a href="https://agentmods.dev/skills/jerry7991/standup-ghost/recap"><img src="https://agentmods.dev/badge/skills/jerry7991/standup-ghost/recap.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 715 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 $0.00084 $0.00715
Opus 5 $0.00042 $0.00358
Sonnet 5 $0.00017 $0.00143
Haiku 4.5 $0.00008 $0.00072

Measured 4d ago against content hash a33110f098ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recap 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 4d 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.

skills/recap/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reads the local archive (~/.local/state/standup-ghost/out/standup-<YYYY-MM-DD>.md — one file per posted day) plus receipts. No network needed for archive-covered ranges; nothing new is stored.

Verbs (ALL on-demand — this skill never runs on a schedule and never auto-posts)

  • recap week|month|quarter|half|year — TLDR of the period ending today.
  • recap <YYYY-MM-DD>..<YYYY-MM-DD> — explicit range.
  • find <query> [range] — where/when a topic appears ("find payment-retry", "find PROJ-42 in Q1").
  • recap team [range] — READ-ONLY digest of the shared canvas: read everyone's dated sections in range (requires the slack-canvas sink configured), group by person/handle, summarize per person + cross-team themes. Uses only what teammates already posted publicly; output stays in chat unless the user explicitly asks to deliver it somewhere.
  • recap sprint — current-sprint slice: filter the range to the active sprint (ask Jira sprint in openSprints() AND assignee = currentUser() for the sprint window/name) and recap just that.

Recap — how to compose

  1. Select archive files in range by filename date (they're self-dated; no index needed).
  2. Aggregate by initiative bucket across days: what LANDED (Yesterday outcomes), sustained threads, one-off wins. Dedupe the daily repetition — a ticket that appeared 9 days collapses to one line with its arc ("PROJ-42: started 03-02, landed 03-18").
  3. Counts from links: distinct tickets touched/closed, PRs merged, review load, meetings-without-tickets.
  4. Output shape (terse, tables-first):
    • One-paragraph TLDR.
    • Per-bucket table: bucket / arc / key links.
    • Numbers row: tickets, PRs, span, days posted vs working days.
  5. Deliver: chat by default; on request, the file sink (out/recap-<range>.md) or self-DM. Never post a recap to team sinks without explicit confirmation.

Gaps are honest, and backfillable

The archive only covers days the file sink was enabled. For gaps in the requested range:

  • Say exactly which spans are missing — never silently pretend coverage.
  • Offer backfill mode: run the source cards (Jira updated >= range, GitHub updated:>=, sessions if within retention) over the missing span and merge, clearly marked "reconstructed from sources, not from posted standups".

Read the full file on GitHub · 34 lines

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. 4d ago First seen · 34 lines · 84 tokens per session scan A a33110f098ff

Subscribe to this mod's changes

recap is a skill published in the GitHub repository jerry7991/standup-ghost (2 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 715 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.

Related

Other skills, from other repositories

remindme

⏰ simple Telegram reminders for OpenClaw. cron, zero dependencies.

CraftOS-dev/CraftBot · 20 tokens

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…

cbrock84/headcount · 93 tokens

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…

cbrock84/headcount · 73 tokens

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…

cbrock84/headcount · 69 tokens

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.

metabase/metabase · 46 tokens

mutation-testing

Run mutation testing on a Clojure namespace, generate tests to kill surviving mutations, and open draft PRs with Linear issue tracking.

metabase/metabase · 30 tokens