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 agentmods add commands/helloruru/claude-memory-engine/reflectgit clone --depth 1 https://github.com/HelloRuru/claude-memory-engineWhat 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 | $0.00000 | $0.01108 |
| Opus 5 | $0.00000 | $0.00554 |
| Sonnet 5 | $0.00000 | $0.00222 |
| Haiku 4.5 | $0.00000 | $0.00111 |
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 2d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reflect — Learning Loop Steps 4-8 (Review -> Organize -> Refine -> Re-learn -> Trim -> Wrap up)
After the user triggers this command, run Learning Loop steps 4-8. Two phases: first half (review + organize) completes, then automatically continues to second half (re-analyze + trim + wrap up).
First Half: Review + Organize (Steps 4-5)
Step 4: Review (read-only, don't change anything yet)
- Read project index: Read
~/.claude/sessions/project-index.md- If the user specifies a project (e.g.,
/reflect blog) → only look at that project's sessions - No project specified → look at all projects
- If the user specifies a project (e.g.,
- Read session summaries: Based on the index, read the last 7 days of session records (max 10)
- Read pitfall records: Scan
~/.claude/skills/learned/auto-pitfall-*.md - Read memory files: Scan all
memory/*.mdfiles - Tag each item (read-only, don't edit yet):
- Each memory paragraph:
active/outdated/duplicate/needs update - Each pitfall record:
internalized(already in CLAUDE.md) /still relevant/can remove
- Each memory paragraph:
Step 5: Refine (act on tags, use the 4-question decision tree)
Run each item through four questions before acting — don't merge mechanically:
- Q1 Still needed? Does this item serve the core workflow? → If not, mark for removal
- Q2 Can condense? Can it merge with another item into a tighter version? → Write the refined version, it naturally replaces the originals
- Q3 Already covered? Is this already covered by a CLAUDE.md rule? → If yes, don't duplicate it in memory
- Q4 Remove as last resort → Only if Q1-Q3 don't apply. Rarely needed
- Merge duplicates: Find duplicate paragraphs in memory/*.md, condense using Q2
- Update outdated: Items tagged "outdated" — use Q1 to decide if they still serve the core workflow
- Relocate: Move misplaced content to the correct HOOK file
Second Half: Re-analyze + Trim + Wrap up (Steps 6-8)
Runs automatically after first half completes. No need for the user to trigger again.
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.
- 2d ago First seen · 107 lines · 0 tokens per session scan A 4d382e7b0589
reflect is a command published in the GitHub repository HelloRuru/claude-memory-engine (133 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,108 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
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
validate-dependencies
Validate all task dependencies for issues.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.