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 pandysp/claude-plugins --skill reflectgit clone --depth 1 https://github.com/pandysp/claude-pluginsWrote 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/pandysp/claude-plugins/reflect)<a href="https://agentmods.dev/skills/pandysp/claude-plugins/reflect"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/reflect/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/pandysp/claude-plugins/reflect"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/reflect.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 | $0.00134 | $0.01358 |
| Opus 5.5 | $0.00054 | $0.00543 |
| Sonnet 5.5 | $0.00027 | $0.00272 |
| Haiku 4.5 | $0.00013 | $0.00136 |
Grade A, and why
reflect 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 23d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflect: surface lessons before they fade
A session ended. The work shipped, or hit a natural pause. The friction, surprises, and insights are still warm in context, but they decay fast. The next session won't remember what surprised you today.
This skill is the discipline of naming what's worth keeping before the context evaporates, and saying where each piece would live. The output is a proposal: lessons phrased the way they would be saved, each with a destination. The writing happens after the user chooses, not before.
What to surface
Five questions to scan. Use only those that have real signal:
- What surprised me? Moments where reality didn't match the prior. Usually the highest-signal lessons.
- What friction repeated? Pain that happened more than once this session. Single occurrences are noise; repeats are signal.
- What habit, if it had been in the instructions, would have prevented today's problem and others like it? A rule or default missing from the host, project, or repository instructions that govern this work.
- What pattern emerged that's worth naming? A recurring shape, idiom, or approach that worked. Naming makes it reusable.
- What's worth saving as a durable note? Knowledge that will be useful in future sessions but doesn't fit anywhere yet.
If a question has no signal, skip it. Reflection isn't a checklist to fill. It's a salvage operation.
Where each lesson would go
Classify the insight before naming a destination. Follow the host and workspace's established hierarchy instead of inventing a new store:
- Behavioral instruction: the applicable host, project, or repository instruction file. Common host-level names include
CLAUDE.mdandAGENTS.md, but the governing workspace instructions decide the real destination and scope. An instruction file is loaded for every future task in its scope: all work for a global file, all work in the project for a project file. An entry belongs there only if it helps with tasks nobody can foresee yet, not just with a repeat of today's. Reword the entry without the specifics of today's incident (its files, commands, tools and people), keeping only names that hold across the file's whole scope. If the reworded entry no longer makes sense, it isn't an instruction: the specific fact goes to notes or docs, and only the habit behind it becomes the rule. Prefer sharpening an existing entry over adding one. - Durable fact: the host's memory mechanism when one exists and the fact belongs there.
- Project or domain knowledge: the existing project notes or documentation closest to the subject.
- Session context: daily or session memory only when the workspace defines it and the information is short-lived.
- Tooling friction: a new or existing ticket when the remedy is a code or process change, not another instruction.
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.
- 23d ago Changed · +1 lines 5c293055d986
- 1mo ago Changed · +15 lines · +20 tokens per session 0f4b79e3abab
- 1mo ago First seen · 55 lines · 114 tokens per session scan A 25cb33a296a5
reflect is a skill published in the GitHub repository pandysp/claude-plugins (6 stars, last pushed 7d ago), licensed MIT. It adds 134 tokens to every session and 1,358 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.