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 jasonm4130/claude-skills/plugin install session-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/jasonm4130/claude-skills/retro)<a href="https://agentmods.dev/skills/jasonm4130/claude-skills/retro"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/retro/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/jasonm4130/claude-skills/retro"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/retro.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 | $0.00128 | $0.02076 |
| Opus 5 | $0.00064 | $0.01038 |
| Sonnet 5 | $0.00026 | $0.00415 |
| Haiku 4.5 | $0.00013 | $0.00208 |
Grade A, and why
retro 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 11d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Retrospective
You are running an interactive session retrospective. Your goal is to walk through this session with the user, understand what happened and why, and write structured memory entries useful in future sessions.
The retro is batch-scoped: it retrospects every unprocessed worthy session
(the sessions in retro-worthy.jsonl not yet in retro-processed.jsonl) plus the
current session, not just the current one — because the end-of-day offer arrives at most once a day,
by which point several worthy sessions may have accrued, and each deserves capture. It reads two
cheap signals: the per-session JSONL event logs (append-only, maintained by the
PostToolUse hook) and live git state for the current tree (git status,
git diff --stat, git log since session start). It does NOT parse the raw session
JSONL transcript and does NOT depend on claude-mem.
Step 1: Collect the batch + quick-skip gate
Run the collector once. It resolves the batch, aggregates each session's event
log, prints the snapshot, and persists it to retro-batch-{sid}.json for Steps 2 and
6 to reuse — do not run it again in later steps.
CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" node "${CLAUDE_PLUGIN_ROOT}/scripts/collect-batch-sessions.mjs" "${CLAUDE_SESSION_ID}"
The snapshot is { boundaryTs, processedSids, totalSessions, cappedFrom?, batch: [ {sid, isCurrent, startDate, edits, writes, bashCalls, filesTouched, reasons, firstTs, lastTs} ] }. Decide on the whole batch: if no session in batch has any edits or
writes, offer to skip.
- If the user declines a skip / there is signal → continue to Step 2.
- If the user accepts the skip (nothing to capture) → still run Step 6 cleanup. A skip is a disposition: marking the batch processed stops a zero-signal batch (e.g. one whose event logs are missing) from re-triggering the nudge forever.
If cappedFrom is set, tell the user only the most-recent sessions are shown and the
rest remain queued for a later retro.
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.
- 11d ago First seen · 213 lines · 128 tokens per session scan A 71dfcf3be766
retro is a skill published in the GitHub repository jasonm4130/claude-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 128 tokens to every session and 2,076 once invoked, about $0.0006 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
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.
recall
Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done this before' or 'how did I fix X' in Elixir/Phoenix work. ccrider MCP when available, else git + solution docs.
assigns-audit
Inspect LiveView socket assigns for memory bloat — missing temporaryassigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporaryassigns.
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.
context-anchoring
Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles).…
learning-harvest
Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time. Provides a protocol for accumulating actionable patterns from practice that complement standards and defaults. Use when a workflow session completes…