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 sramji/awesome-superpowers --skill end-of-session-reflectiongit clone --depth 1 https://github.com/sramji/awesome-superpowersWrote 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/sramji/awesome-superpowers/end-of-session-reflection)<a href="https://agentmods.dev/skills/sramji/awesome-superpowers/end-of-session-reflection"><img src="https://agentmods.dev/badge/skills/sramji/awesome-superpowers/end-of-session-reflection/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/sramji/awesome-superpowers/end-of-session-reflection"><img src="https://agentmods.dev/badge/skills/sramji/awesome-superpowers/end-of-session-reflection.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 | $0.00055 | $0.01762 |
| Opus 5 | $0.00028 | $0.00881 |
| Sonnet 5 | $0.00011 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
end-of-session-reflection 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-of-Session Reflection
Overview
Structured review at the end of every work session that harvests learnings and routes them into future session plans. Prevents knowledge loss between sessions.
Scope
This skill covers development work — code, architecture, tooling, configuration, and skills. It does not try to track non-development activity.
When to Use
- User says "let's wrap up", "that's it for today", "we're done"
- Last step of a session plan is complete
- About to write a session summary
- About to update the project's build/dev log
- User asks to commit final session work
Core Process
digraph reflection {
rankdir=TB;
harvest [label="1. Harvest\nWhat happened vs plan?" shape=box];
prompt [label="2. Prompt user\nAnything I missed?" shape=box];
categorize [label="3. Categorize\neach learning" shape=box];
route [label="4. Route\nto future sessions" shape=box];
propose [label="5. Show proposed\nedits to user" shape=box];
write [label="6. Write summary\n+ update dev log" shape=box];
harvest -> prompt -> categorize -> route -> propose -> write;
}
1. Harvest Learnings
Walk through the development work in the session and identify. Skip non-development activity entirely — if it didn't change code, config, architecture, or tooling, it doesn't belong here.
- What changed from the plan? Steps skipped, reordered, or added
- What broke and how was it fixed? Bugs, workarounds, quirks
- Did any tool errors reveal ergonomic gaps? When a tool fails because of how it was invoked (wrong directory, unexpected input format, missing auto-detection), that's a signal the tool isn't agent-native enough. A bug is "the code is wrong"; an ergonomic gap is "the code works as designed but the design doesn't match how agents use it." Capture these as improvement candidates — they compound across every future session.
- What surprised us? Unexpected behavior, UX gaps, missing requirements
- What did the user express a preference about? Workflow, UX, architecture, scope
- What scope changed? New dev requirements discovered, things deferred, things escalated (code/architecture only)
- What is now dead code or dead plan? If architectural decisions or scope changes made existing code, stubs, plan steps, or agent files unnecessary, identify them for deletion. Never carry forward mistakes or technical debt into the next session.
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 · 147 lines · 55 tokens per session scan A a9420115139b
end-of-session-reflection is a skill published in the GitHub repository sramji/awesome-superpowers (3 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 1,762 once invoked, about $0.0003 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
context-compression
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions.
context-degradation
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
context-fundamentals
This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other…
context-optimization
This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality.
filesystem-context
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup policies for context stored outside the prompt.
memory-systems
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to…