agentmods.dev

session-recap

session-recap is a skill for Claude Code from sxhmilyoyo/sundayhao-plugins. It costs 39 tokens per session (9,229 once invoked), scanned A, original, Apache-2.0.

A workflow for turning a Claude Code session into concise, linked project documentation. It extracts decisions, workflows, and edge cases into a knowledge bank rather than keeping a full transcript.

In plain words
What is it for?
Use it to summarize a finished coding session, capture reusable knowledge, and link the result to related project notes.
Why use it?
It preserves useful lessons from completed work without requiring someone to reread a long session transcript. It is intended to run in a new session after the work ends.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is source ../common/resolve_project.sh.

Part of the second-brain plugin — 6 skills shipped together

not rated 8repo changed 6d ago A scan 39 tokens original Apache-2.0

Good fit Use it to summarize a finished coding session, capture reusable knowledge, and link the result to related project notes.

Compare 6 skills from other repositories ↓
View source ↗ sxhmilyoyo/sundayhao-plugins
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/sxhmilyoyo/sundayhao-plugins
agentmods
npx agentmods add skills/sxhmilyoyo/sundayhao-plugins/session-recap

Made for: Claude Code.

Or install second-brain, the plugin that ships this one along with the rest of its 6 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 session-recap

README.md
[![agentmods](https://agentmods.dev/badge/skills/sxhmilyoyo/sundayhao-plugins/session-recap/github.svg)](https://agentmods.dev/skills/sxhmilyoyo/sundayhao-plugins/session-recap)
Your own site
<a href="https://agentmods.dev/skills/sxhmilyoyo/sundayhao-plugins/session-recap"><img src="https://agentmods.dev/badge/skills/sxhmilyoyo/sundayhao-plugins/session-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.

agentmods 80×15 button for session-recap

Your own site · 80×15
<a href="https://agentmods.dev/skills/sxhmilyoyo/sundayhao-plugins/session-recap"><img src="https://agentmods.dev/badge/skills/sxhmilyoyo/sundayhao-plugins/session-recap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,229 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.09229
Opus 5.5 $0.00016 $0.03692
Sonnet 5.5 $0.00008 $0.01846
Haiku 4.5 $0.00004 $0.00923

Measured 6d ago against content hash c22b9a7f0ebe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

session-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 6d ago.

The scan reads SKILL.md. This mod also ships 12 executable files (scripts/analyze_for_distillation.sh, scripts/count_wikilinks.sh, scripts/detect_external_docs.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

second-brain/skills/session-recap/SKILL.md · 759 lines

How it starts

The opening of the file, as written. The whole thing — 759 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Recap

Systematically document Claude Code sessions into the knowledge bank.

Knowledge Bank Location: Read from ~/.claude/plugins/config/second-brain/config.json. Configure via skills/common/setup_kb_path.sh --configure.

Philosophy: Knowledge Bank = BRAIN, not ARCHIVE. Preserve workflows, edge cases, decisions—not verbose traces. Target 95% size reduction, 100% actionable knowledge.

Invocation

Recommended Workflow

Important: a recap runs in a dedicated recap session, started by the launcher. Not in the session being recapped, and not in whatever session you happen to have open. Phase 1.0 stops it otherwise.

  1. Exit the work session. The SessionEnd hook finishes session.md and, when auto_recap is not off, stamps recap_status: requested on it.

  2. Start the recap through the launcher, which is also the command the start-of-session notice prints:

    <plugin root>/hooks/scripts/recap_launcher.sh --manual {KB_PATH}/_sessions/YYYY-MM-DD/{session_id}/

    Inside Herdr this runs the recap in the pane you typed it in, if that pane is at a shell prompt, and opens one beside it if something is already running there — which is the case when a session runs this through its Bash tool. Anywhere else it prints a command to paste into a new terminal. Either way the recap session carries SECOND_BRAIN_RECAP_OF, which is what makes its own hooks register it as a recap and never recap it in turn (ADR-0003).

Typing /second-brain:session-recap <folder> into an ordinary session stops at the gate on purpose. That session has no recap_of, so finishing the recap there would either write the subject's description onto the wrong note or leave this session to be recapped as if it had done the work.

Legacy: Raw Transcript Path

If no session folder exists (e.g., hooks were not configured), you can still provide a raw .jsonl transcript path:

Recap the session at /path/to/session-id.jsonl

Read the full file on GitHub · 759 lines

Files

What ships with it

28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago Changed c22b9a7f0ebe
  2. 19d ago Changed · +100 lines 5afd73f45a7e
  3. 1mo ago Changed · +160 lines 770cfe6376df
  4. 1mo ago Changed · +7 lines 54025bb7898c
  5. 1mo ago First seen · 492 lines · 39 tokens per session scan A e5b7374ce501

Subscribe to this mod's changes

session-recap is a skill published in the GitHub repository sxhmilyoyo/sundayhao-plugins (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 39 tokens to every session and 9,229 once invoked, about $0.0002 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 2026-08-31.

Memory and contextWriting and docsagentic-workflowai-memoryclaude-code-pluginclaude-code-pluginsclaude-code-skillscontext-window-optimization
Related

Other skills, from other repositories

evolving-status

View Self-Evolving Loop session status, history, and memory metrics.

claude-world/director-mode-lite · 17 tokens

dream

Check this project's memory notes against the repo, fix the ones that went false, and tidy the index, as one git commit you can revert. Checks only notes that are new or name a changed file; pass all to check every note. Costs one Sonnet call per 15 notes, plus one.

saadshahd/moo.md · 65 tokens

pocket-init

Onboards an existing project onto Pocket by scanning its local configuration, writing a merge-safe project guide, and optionally calibrating a local Pocket Education learner profile. Trigger on "pocket-init", "set up pocket", "onboard this project", "generate CLAUDE.md", "generate AGENTS.md", or "enable education…

rfxlamia/pocketto · 72 tokens

learn-from-fix

Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.

oliver-kriska/claude-elixir-phoenix · 46 tokens

compound-docs

Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.

oliver-kriska/claude-elixir-phoenix · 38 tokens

cdb-scan

Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map…

Avijit07x/claude-db · 72 tokens