Borrowing it
Nothing to install: this file belongs to Benkapner/claude-code-basecamp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Benkapner/claude-code-basecamp/main/.claude/commands/recap.mdgit clone --depth 1 https://github.com/Benkapner/claude-code-basecampWrote 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/commands/benkapner/claude-code-basecamp/recap)<a href="https://agentmods.dev/commands/benkapner/claude-code-basecamp/recap"><img src="https://agentmods.dev/badge/commands/benkapner/claude-code-basecamp/recap/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/commands/benkapner/claude-code-basecamp/recap"><img src="https://agentmods.dev/badge/commands/benkapner/claude-code-basecamp/recap.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 | $0.00026 | $0.00628 |
| Opus 5.5 | $0.00010 | $0.00251 |
| Sonnet 5.5 | $0.00005 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
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 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recap Command
Summarize the current work session into a structured, shareable update.
Instructions
Step 1: Gather What Happened
# Recent commits (this session's work)
git log --oneline --since="8 hours ago" 2>/dev/null || git log --oneline -15
# What files changed
git diff --stat HEAD~10..HEAD 2>/dev/null || git diff --stat
# Current status
git status --short
Also review the conversation history for:
- What the user asked for
- Key decisions made (and why)
- Problems encountered and how they were solved
- Skills, agents, or commands that were used
Step 2: Generate the Recap
Format the output like this:
SESSION RECAP
=============
Date: [today's date]
Repo: [repository name]
WHAT WAS DONE:
1. [Change #1 — one sentence describing what and why]
2. [Change #2 — one sentence]
3. [Change #3 — one sentence]
...
KEY DECISIONS:
- [Decision and reasoning — e.g., "Kept closed issues as lightweight entries
instead of removing them, to give the AI context about completed work"]
- [Decision and reasoning]
PROBLEMS SOLVED:
- [Problem → Solution — e.g., "Merge conflict on executive_report.html
→ skipped local commit, kept remote version"]
FILES CHANGED:
[X] files modified, [Y] files created, [Z] files deleted
TESTS:
[All N tests passing / X failures]
READY TO SHARE (copy-paste for standup/Slack/email):
──────────────────────────────────────────────────────
[2-3 sentence summary suitable for a non-technical audience.
Focus on WHAT was accomplished and WHY it matters,
not the technical details of HOW.]
──────────────────────────────────────────────────────
Step 3: Offer Follow-ups
After the recap, ask:
- "Want me to adjust the tone (more technical / more executive)?"
- "Want me to expand any section?"
- "Want me to draft a message for a specific person?"
Important
- The "READY TO SHARE" section should be copy-pasteable as-is — no markdown, no jargon
- Focus on outcomes ("split the pipeline for easier debugging") not mechanics ("edited 14 files")
- If multiple repos were touched, organize by repo
- Include commit hashes for traceability
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 First seen · 89 lines · 26 tokens per session scan A c1c995680ca3
recap is a command published in the GitHub repository Benkapner/claude-code-basecamp (18 stars, last pushed 27d ago), licensed MIT. It adds 26 tokens to every session and 628 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
firm
Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved.
promote
The promote loop — scan your transcripts for what you keep asking, pick a pattern, draft the skill, test its triggers, publish the release package.
ship-a-feature
Workflow recipe — take a feature idea from fuzzy brief to launch plan by chaining 5 skills.
cn-career-ladder
A workflow that turns Chinese workplace notes into a promotion case through five stages: weekly reports, a yearly review, a presentation outline, and interview practice. It carries each stage's output into the next.
rescue-an-account
Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
setup-context
Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you.