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/HelloRuru/claude-memory-engineWrote 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/helloruru/claude-memory-engine/analyze)<a href="https://agentmods.dev/commands/helloruru/claude-memory-engine/analyze"><img src="https://agentmods.dev/badge/commands/helloruru/claude-memory-engine/analyze/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/helloruru/claude-memory-engine/analyze"><img src="https://agentmods.dev/badge/commands/helloruru/claude-memory-engine/analyze.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 | $0.00010 | $0.00293 |
| Opus 5.5 | $0.00004 | $0.00117 |
| Sonnet 5.5 | $0.00002 | $0.00059 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
analyze 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 1mo 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
/analyze — Record Corrections
Compare the user's edits against your output. Find what you got wrong and why.
Steps
- Find the diff — Identify what the user changed in your output (text, code, structure, tone)
- Check against rules — Compare each correction against existing rules in CLAUDE.md, memory files, and learned skills
- Log missed rules — If a rule exists but you didn't follow it, log it with a count (e.g., "2nd time missing this")
- Distill new patterns — If the correction doesn't match any existing rule, distill it into a new one
- Save to error notebook — Append to
~/.claude/skills/learned/writing-review-list.md(or project-specific file) - Report — Tell the user: "Logged N corrections. M were known rules I missed, K are new patterns."
Error notebook format
### Rule name
- **Rule:** What to do
- **Missed:** N times
- **Status:** active / cleared
- **Example:** What went wrong → what was correct
When to run
Run this right after the user corrects your work. The fresher the context, the better the analysis.
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.
- 1mo ago First seen · 31 lines · 10 tokens per session scan A af97a85c9914
analyze is a command published in the GitHub repository HelloRuru/claude-memory-engine (134 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 293 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
watch
You are executing the /hydra:watch command. Live monitoring of all background agents with real-time status updates.
golden-path
The golden path. One command, idea to merged PR. Runs the full pipeline, prd → prp → plan → dev → test → pr, with sensor + eval gates at every stage.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
render
Inspect an archived transcript (gzipped) — show counts, tool calls, errors. Useful after a PreCompact or SessionEnd, before deciding to write a retroactive /continuum:checkpoint.