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.
npx skills add Szotasz/marveen --skill retrospectivegit clone --depth 1 https://github.com/Szotasz/marveenWrote 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/szotasz/marveen/retrospective)<a href="https://agentmods.dev/skills/szotasz/marveen/retrospective"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/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.
<a href="https://agentmods.dev/skills/szotasz/marveen/retrospective"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 Rogue Agent · line 142 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Agent Snooping · line 55 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Rogue Agent · line 86 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.
- medium Data Exfiltration · line 148 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00064 | $0.01411 |
| Opus 5 | $0.00032 | $0.00705 |
| Sonnet 5 | $0.00013 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade B, and why
retrospective scanned grade B with 2 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/ | head -30 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $(cat store/.dashboard-token)" \ How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospective -- Session Analysis & Improvement
When to use
- After a complex session (5+ tool calls, error recovery, multi-step workflow)
- When the user corrected your approach ("no, do it this way")
- After a failed attempt that required a different strategy
- Before context window exhaustion on a productive session
- Explicitly via
/retrospectivecommand
Arguments
| Argument | Required | Description |
|---|---|---|
scope |
no | What to analyze: session (default), last-task, last-hour |
focus |
no | Narrow analysis: skills, memory, workflow, or all (default) |
Examples:
/retrospective-- full session analysis/retrospective scope=last-task focus=skills-- only skill improvements for the last task/retrospective focus=memory-- only memory tier/content suggestions
Procedure
1. Gather session data
Collect from the current conversation context:
- What tasks were attempted
- Which approaches succeeded vs failed
- User corrections and their reasoning
- Tools/skills used and their effectiveness
- Errors encountered and how they were resolved
- Time spent on dead ends vs productive work
Also pull external state:
AGENT_ID="$(echo $BOT_NAME | tr '[:upper:]' '[:lower:]')"
# Recent memories written this session
curl -s -H "Authorization: Bearer $(cat store/.dashboard-token)" \
"http://localhost:3420/api/memories?agent=$AGENT_ID&category=hot&limit=20"
# Today's daily log entries
DATE=$(date +%Y-%m-%d)
curl -s -H "Authorization: Bearer $(cat store/.dashboard-token)" \
"http://localhost:3420/api/daily-log?agent=$AGENT_ID&date=$DATE"
# Skills that were referenced or used
ls ~/.claude/skills/ | head -30
2. Analyze with A/B/C framework
For each significant event in the session, evaluate:
A -- What happened? State the fact: what was attempted, what was the outcome.
B -- Why did it happen that way? Root cause: was it a missing skill, wrong memory tier, incorrect assumption, tooling gap, or communication issue?
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 · 170 lines · 64 tokens per session scan B 79849f31769e
retrospective is a skill published in the GitHub repository Szotasz/marveen (98 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 1,411 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
family-knowledge
Family knowledge base for recording and retrieving household facts (members, allergies, dietary rules, doctors, schedules, house rules, pets, important dates).
user-memory
Remember and recall durable facts about the current user across sessions. Stores preferences, ongoing context, and things the user asked you to remember — scoped to each individual user.
openopc
An organisation runtime for turning an AI assistant into a group of role-based workers. It creates an organisation structure, breaks work into dependent tasks that can run in parallel, tracks approvals and handoffs, and stores organisational memory.
openakashic
Persistent memory for AI agents across sessions. Search what others figured out, write what you learn, publish what deserves a wider audience.
hive-mind-advanced
Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory.