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/rtk-ai/rtk/repo-recapnpx skills add rtk-ai/rtk --skill repo-recapgit clone --depth 1 https://github.com/rtk-ai/rtkWhat 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 | $0.00034 | $0.01814 |
| Opus 5 | $0.00017 | $0.00907 |
| Sonnet 5 | $0.00007 | $0.00363 |
| Haiku 4.5 | $0.00003 | $0.00181 |
Grade A, and why
repo-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 2d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Recap
Generate a structured recap of the repository state: open PRs, open issues, recent releases, and executive summary. Output is formatted as Markdown with clickable GitHub links, ready to share.
Language
- Check the argument passed to this skill
- If
enorenglish→ produce the recap in English - If
fr,french, or no argument → produce the recap in French (default)
Preconditions
Before gathering data, verify:
# Must be inside a git repo
git rev-parse --is-inside-work-tree
# Must have gh CLI authenticated
gh auth status
If either fails, stop and tell the user what's missing.
Steps
1. Gather Data
Run these commands in parallel via gh CLI:
# Repo identity (for links)
gh repo view --json nameWithOwner -q .nameWithOwner
# Open PRs with metadata
gh pr list --state open --limit 50 --json number,title,author,createdAt,changedFiles,additions,deletions,reviewDecision,isDraft
# Open issues with metadata
gh issue list --state open --limit 50 --json number,title,author,createdAt,labels,assignees
# Recent releases (for version history)
gh release list --limit 5
# Recently merged PRs (for contributor activity)
gh pr list --state merged --limit 10 --json number,title,author,mergedAt
Note: author in JSON results is an object {login: "..."} — always extract .author.login when processing.
2. Determine Maintainers
To distinguish "our PRs" from external contributions:
gh api repos/{owner}/{repo}/collaborators --jq '.[].login'
If this fails (permissions), fallback: authors with write/admin access are those who merged PRs recently. When in doubt, ask the user.
3. Analyze and Categorize
PRs — Categorize into 3 groups:
Our PRs (author is a repo collaborator):
- List with PR number (linked), title, size (+additions, files count), status
External — Reviewable (manageable size, no major blockers):
- Additions ≤ 1000 AND files ≤ 10
- No merge conflicts, CI not failing
- Include: PR link, author, title, size, review status, recommended action
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.
- 2d ago First seen · 217 lines · 34 tokens per session scan A 165e7ac9fda7
repo-recap is a skill published in the GitHub repository rtk-ai/rtk (78,131 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 1,814 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
orchestrator-lanes
Claude Code dev-orchestrator only. File-based multi-lane PM playbook (score, DAG, run-controller, L0/L1/L2, ship). Use when this session IS that agent, or user says info / справка / lane-stack:orchestrator-lanes info. SKIP: Grok, Codex, Kimi, Qwen, AGY, Cursor writer CLIs and any default coding agent — do not load, do…
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
info
Lane-stack work-process cheat sheet. Catalog of resume, onboard, architect a new app, design, docs. Use when user says info, справка, lane-stack:info, /lane-stack:info, что умеет стек, как запускать.
lane-memory
SMA-style project fact corpus under .agents/memory/. Opt-in via adoc stages.memory.enabled. Use when user says память, lane-memory, corpus, CORE, почему бот забыл, or an agent needs durable non-code facts. Not PROGRESS/LESSONS dumps.
source-command-ccguide-daily
Daily update check — official Anthropic docs diff + guide/CC releases digest.