session-retrospective

session-retrospective is a skill for Claude Code from arozumenko/sdlc-skills. It costs 46 tokens per session (1,106 once invoked), scanned A, original, MIT.

A read-only review of earlier coding-agent conversations and helper-agent sessions that extracts possible improvements for team memory and working habits.

In plain words
What is it for?
Use it after recent work to identify delays, propose memory updates, and suggest workflow improvements based on past sessions.
Why use it?
It reveals repeated wasted effort and useful facts from past work without changing shared files before a person approves the suggestions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Part of the sdlc-skills plugin — 53 skills shipped together

Good fit Use it after recent work to identify delays, propose memory updates, and suggest workflow improvements based on past sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arozumenko/sdlc-skills/session-retrospective
Install

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.

Any agent
npx skills add arozumenko/sdlc-skills --skill session-retrospective
Clone the repo
git clone --depth 1 https://github.com/arozumenko/sdlc-skills

Made for: Claude Code.

Or install sdlc-skills, the plugin that ships this one along with the rest of its 53 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-retrospective

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/session-retrospective"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/session-retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,106 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 93
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
  • medium Rogue Agent · line 18
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00046 $0.01106
Opus 5 $0.00023 $0.00553
Sonnet 5 $0.00009 $0.00221
Haiku 4.5 $0.00005 $0.00111

Measured 10d ago against content hash 02941dcd1183, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

session-retrospective 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/distill-sessions.mjs, scripts/distill-sessions.test.mjs), 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.

bundles/feature-development/skills/session-retrospective/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Retrospective

Distill past sessions for this project into evidenced, ack-gated improvements to the team's memory and shared docs. Efficiency-led: process waste first, durable facts second. You (scout) run this manually when asked.

Read-only analysis, assisted writes. The parser only reads transcripts. You propose every change and write nothing until the user acks.

When to use

  • The user says "run a retrospective", "mine past sessions", "what slowed us down", or "improve the team from recent work".
  • Periodically, to fold lessons from recent sessions into .agents/.

Not for: onboarding a fresh repo (that's seeding-a-project), or refreshing config from code/PR changes (that's scout's normal update flow).

Procedure

  1. Distill. Run the parser from the project root:

    node {skill}/scripts/distill-sessions.mjs
    

    It reads ~/.claude/projects/<this-project>/ transcripts newer than the watermark (.agents/memory/scout/.last-retrospective), plus each session's subagents/, and prints a bounded markdown digest. Add --all to ignore the watermark, --exclude-session <id> to skip the active session, or --out <path> to save the digest. Exit code 3 = no transcripts found → use the Fallback below. The newest session is usually the one you're running in — pass --exclude-session <its id> so the retrospective doesn't analyze itself.

  2. Read the digest (it fits in context — never read raw .jsonl).

  3. Interpret — see references/signal-taxonomy.md. Separate:

    • Efficiency findings — repeated corrections, retry loops, file churn, tool errors, ignored conventions.
    • Durable facts — gotchas, decisions, "X doesn't work, use Y". Every finding MUST cite the session id it came from. Drop anything you cannot evidence from the digest.
  4. Map findings to targets — see references/finding-to-target.md: role-specific → that role's .agents/memory/<role>/; team-wide process → .agents/workflow.md / .agents/conventions.md; durable fact → a curated entry (via the memory skill). If .agents/ doesn't exist, the project isn't seeded — a retrospective refines an existing lens, it doesn't create one; run seeding-a-project first.

Read the full file on GitHub · 103 lines

Files

What ships with it

6 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. 10d ago First seen · 103 lines · 46 tokens per session scan A 02941dcd1183

Subscribe to this mod's changes

session-retrospective is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 1,106 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

shellm

Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.

laude-institute/headlong · 49 tokens