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.
git clone --depth 1 https://github.com/smrafiz/claude-superchargerWrote 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/commands/smrafiz/claude-supercharger/reflect)<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/reflect"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/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/commands/smrafiz/claude-supercharger/reflect"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/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 | $0.00000 | $0.00376 |
| Opus 5 | $0.00000 | $0.00188 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00038 |
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 9d 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.
What it actually says
Score this session and write quality observations to memory: $ARGUMENTS
Run after completing significant work. Scores what worked, what didn't, and writes structured observations that future sessions will load — building a project-specific improvement signal over time.
Do NOT summarize what was done. Focus only on quality signals: what patterns helped, what went wrong, what should change next time.
Step 1 — Score the session
Assess across four dimensions (0–3 each):
| Dimension | 0 | 3 |
|---|---|---|
| Accuracy | Multiple wrong assumptions, rework required | First-attempt correct, no backtracking |
| Scope discipline | Drifted beyond what was asked | Stayed tightly scoped |
| Verification | Claimed done without evidence | Ran checks, confirmed output |
| Efficiency | Many redundant tool calls / retries | Direct path to solution |
Step 2 — Extract observations
For each dimension scored < 2, write one observation:
- What went wrong (specific, not generic)
- Why it happened
- What to do differently next time
For each dimension scored 3, write one observation if a non-obvious approach worked well.
Step 3 — Append to .claude/session-observations.md
Create if absent. Prepend new entry (most recent first):
## YYYY-MM-DD — [one-line description of work done]
Scores: accuracy=N scope=N verification=N efficiency=N
Observations:
- [observation 1 — what + why + next time]
- [observation 2 — what + why + next time]
Cap file at 50 entries — trim oldest if exceeded.
Step 4 — Confirm
State: Reflection written. [N] observation(s) logged to .claude/session-observations.md
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.
- 9d ago First seen · 46 lines · 0 tokens per session scan A 6d27f9037091
reflect is a command published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 376 tokens. 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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.
recall
Search past tool-call observations with BM25 ranking to answer "have I seen this before?" before re-deriving a fix or repeating a mistake. Enforces Law 1 (Research Before Executing).