Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add juanmhidalgo/claude-plugins/plugin install retroWrote 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/skills/juanmhidalgo/claude-plugins/session)<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/session"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/session/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/skills/juanmhidalgo/claude-plugins/session"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/session.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 | $0.00173 | $0.01909 |
| Opus 5.5 | $0.00069 | $0.00764 |
| Sonnet 5.5 | $0.00035 | $0.00382 |
| Haiku 4.5 | $0.00017 | $0.00191 |
Grade A, and why
session 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 14d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Retrospective
Turns a Claude Code session into config changes, not a report nobody reads.
Scope guard
One project at a time. ~/.claude/projects/ holds transcripts from every repo ever
opened here, including work ones — never widen to all projects, and never read another
project's logs unless the user names it.
The one exception is plugin mode (below): it reads plugin-recorder's files from every project, which hold names, counts, durations and statuses only — no prompts, no tool inputs, no paths beyond a project's basename. It never opens another project's transcript.
Pick the mode
| The user asks | Mode |
|---|---|
| "how did that session go", "analyze the last N sessions" | Full — Phases 1–4 |
"how did <plugin> behave", "why was /x:y slow over there", or pastes a session ID from another project |
Plugin — below, then Phases 2–4 on its output |
"what should go in CLAUDE.md / memory from this session", --light |
Light — below; no log analysis |
Plugin mode
Do not ask for session IDs. Run:
${CLAUDE_PLUGIN_ROOT}/scripts/plugin-runs.sh <plugin> [--days N] [--project <basename>]
${CLAUDE_PLUGIN_ROOT}/scripts/plugin-runs.sh --list # which plugins were recorded
It reports invocations by command and version, subagent calls and failures by
subagent_type, turn durations, and a per-project breakdown. If it prints No plugin-recorder data found, say so, suggest installing the plugin-recorder plugin, and
fall back to asking which project to read — the old path, one project at a time. Cite the
script's lines as evidence; a failure row with no session in this project cannot be read
deeper, so do not guess at its cause.
Light mode
Only the current session, from the conversation already in context — no digest, no log
reads. List what a fresh session would have needed to know: corrections the user gave,
facts discovered the hard way, commands that turned out to be the right ones. For each,
name the destination (project CLAUDE.md, a memory file, or nothing if it is one-off) and
quote the exact text to add. Then ask which to apply. Skip Phases 1–3.
What ships with it
2 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.
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.
- 14d ago Changed · +66 lines · +41 tokens per session 180b34274b5d
- 1mo ago First seen · 105 lines · 132 tokens per session scan A 5406f065d880
session is a skill published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 173 tokens to every session and 1,909 once invoked, about $0.0007 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 2026-09-16.
Other skills, from other repositories
socratic
Use after a feature merges or ships, to put seven questions to recently shipped work — confidence, blind spots, decay, unstated assumptions, and what should exist next. Takes an argument naming the target — a feature, a change set (PR, branch, commit range), or the whole repository. Trigger phrases — socratic…
session-retrospective-miner
Automatically mines Claude session JSONL and EVOKORE session data to compute efficiency metrics and produce a structured retrospective report with specific narrative improvement recommendations.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.