agentmods.dev

retrospect-collab

retrospect-collab is a skill for Claude Code from digital-stoic-org/agent-skills. It costs 61 tokens per session (597 once invoked), scanned A, original, MIT.

A session-review tool that examines how you and an AI worked together, including prompts, tool use, and decisions.

In plain words
What is it for?
Use it to review collaboration quality, measure session patterns, and identify ways to improve how you guide an AI assistant.
Why use it?
It helps reveal unclear instructions, poor context sharing, over-trust, and other collaboration patterns that are hard to notice while working.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the retrospect plugin — 3 skills shipped together

not rated 20repo 12d ago A scan 61 tokens original MIT

Good fit Use it to review collaboration quality, measure session patterns, and identify ways to improve how you guide an AI assistant.

Compare 6 skills from other repositories ↓
View source ↗ digital-stoic-org/agent-skills
Install

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.

Claude Code
/plugin marketplace add digital-stoic-org/agent-skills
Claude Code
/plugin install retrospect

Made for: Claude Code.

Or install retrospect, the plugin that ships this one along with the rest of its 3 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 retrospect-collab

README.md
[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/retrospect-collab/github.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/retrospect-collab)
Your own site
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/retrospect-collab"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/retrospect-collab/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 retrospect-collab

Your own site · 80×15
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/retrospect-collab"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/retrospect-collab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 597 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 $0.00061 $0.00597
Opus 5.5 $0.00024 $0.00239
Sonnet 5.5 $0.00012 $0.00119
Haiku 4.5 $0.00006 $0.00060

Measured 1mo ago against content hash 7f85108c8f2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

retrospect-collab 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 1mo 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.

retrospect/skills/retrospect-collab/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retrospect Collab — Collaboration Analysis

Role: Expert in collaboration analysis, agile retrospectives, human-AI interaction patterns, and cognitive skill development.

Analyze sessions across two dimensions:

  1. Technical effectiveness: Context management, guidance quality, critical thinking, bias awareness
  2. Cognitive posture: Intentionality, agency, impact categorization, skill progression

Steps

  1. Filter sessions:

    bash ${CLAUDE_PLUGIN_ROOT}/scripts/retrospect-load-sessions.sh $@

    First line: PERIOD: YYYY-MM-DD_to_YYYY-MM-DD. Remaining: session paths.

  2. Read sessions — extract: user_prompts, tool_calls, duration_seconds, subagent_spawns, JSONL events

  3. Analyze technical effectiveness:

    • Context Management: preparation, over/under-dump, progressive feeding
    • Guidance: prompt clarity, exploration vs constraints balance
    • Critical Thinking: user challenges, AI pushback, alternative-seeking
    • Bias: over-trust, dismissal, confirmation bias, automation bias

  4. Analyze cognitive posture:

    • Intentionality: structured prompts vs trial-and-error, "why before how"
    • Agency: custom construction vs template copy-paste, decision ownership
    • Impact: categorize each session (Automation / Low-impact / High-impact augmentation)
    • Progression: session 1→N sophistication, prompt evolution, strategic vs tactical

  5. Generate Start/Stop/Continue with specific session examples

  6. Write insights to .retro/insights/collab/{PERIOD}.md

  7. Report: file path, suggest /retrospect report for aggregates

Key Principles

  • Evidence-only: Reference actual prompts/tools from sessions, don't invent issues
  • Quantify: "3 out of 8 sessions showed X", not vague generalizations
  • Impact targets: >60% high-impact augmentation, <20% automation
  • Longitudinal: Track skill evolution, not just point-in-time

See reference.md for report template, scoring criteria, impact indicators, and analysis questions.

Read the full file on GitHub · 57 lines

Files

What ships with it

1 file 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. 1mo ago First seen · 57 lines · 61 tokens per session scan A 7f85108c8f2d

Subscribe to this mod's changes

retrospect-collab is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 12d ago), licensed MIT. It adds 61 tokens to every session and 597 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 2026-09-04.

Analytics and metrics
Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens