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/rad-security/claude-code-plugin/recapnpx skills add rad-security/claude-code-plugin --skill recapgit clone --depth 1 https://github.com/rad-security/claude-code-pluginWhat 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 | $0.00045 | $0.00910 |
| Opus 5 | $0.00023 | $0.00455 |
| Sonnet 5 | $0.00009 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
recap scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentKeeper Session Recap
You are producing a security-aware summary of the current Claude Code session by reading local session data.
Step 1: Locate Session Data
Check for the session log file:
AGENTKEEPER_DIR="$HOME/.agentkeeper-plugin"
[ -n "$CLAUDE_PLUGIN_DATA" ] && AGENTKEEPER_DIR="$CLAUDE_PLUGIN_DATA"
cat "$AGENTKEEPER_DIR/sessions/current.jsonl" 2>/dev/null
If the file does not exist or is empty:
Display:
AgentKeeper Session Recap
No session data found.
Session tracking begins after the first tool call in an AgentKeeper-enabled
session. The AgentKeeper hooks record tool calls, file changes, and threat
detections to a local session log.
If you just installed the plugin, start a new session and the recap will
be available after some tool activity.
In the meantime, try:
/agentkeeper:audit — check your Claude Code security setup
/agentkeeper:secrets — scan for exposed secrets in this directory
Stop here if no data exists.
If the file exists:
Read the full contents. Each line is a JSON object representing a hook event. Parse the entries to extract the information below.
Step 2: Analyze Session Data
From the JSONL entries, compute the following:
Tool Call Counts
Count events grouped by tool name (Bash, Edit, Write, Read, Glob, Grep, WebFetch, WebSearch, etc.). Display as a simple table.
Files Modified
Extract unique file paths from Edit and Write tool events. List them.
Files Created
Extract file paths from Write events where the file was newly created (if distinguishable from the event data).
Bash Commands Executed
Extract command strings from Bash tool events. Summarize them — show the first 80 characters of each, truncating long commands. Group similar commands if there are many.
Network Requests
Extract URLs from WebFetch events. List unique domains accessed.
Threats Detected
Look for entries where the hook response contained a threat detection (events with verdict of warn or block, or entries with pattern or threat fields). List each with severity and pattern name.
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.
- yesterday First seen · 129 lines · 45 tokens per session scan A 8e84ae74178d
recap is a skill published in the GitHub repository rad-security/claude-code-plugin (2 stars, last pushed 26d ago), licensed MIT. It adds 45 tokens to every session and 910 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…