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 janbjorge/rekal --skill rekal-hygienegit clone --depth 1 https://github.com/janbjorge/rekalWrote 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/janbjorge/rekal/rekal-hygiene)<a href="https://agentmods.dev/skills/janbjorge/rekal/rekal-hygiene"><img src="https://agentmods.dev/badge/skills/janbjorge/rekal/rekal-hygiene/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/janbjorge/rekal/rekal-hygiene"><img src="https://agentmods.dev/badge/skills/janbjorge/rekal/rekal-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.00878 |
| Opus 5 | $0.00039 | $0.00439 |
| Sonnet 5 | $0.00015 | $0.00176 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
rekal-hygiene 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 12d 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.
Find and fix problems in the rekal database. Every change requires explicit user approval. Never auto-delete. Never auto-modify.
Step 1: Health overview
rekal health
Report one line:
"142 memories across 3 projects, spanning 6 months."
Step 2: Audit the full store
rekal export
This prints every memory as JSON (id, content, project, tags, timestamps). Read it and group entries that cover the same fact/preference/procedure.
Per finding, classify and propose:
Issue?
├── Duplicates / same topic stored twice
│ └── Identify the most complete version, propose replacing the others:
│ memory_store(content="<best content>", replaces="<older id>")
│
├── Contradiction: one outdated, one current
│ └── Propose: memory_store(content="<current content>", replaces="<outdated id>")
│
├── Contradiction: unclear which is correct
│ └── Ask user: "Which is correct? [A] or [B]?"
│
├── Project-specific content but project missing
│ └── Propose: memory_store(content="<same content>", project="<name>", replaces="<id>")
│
├── Content < 20 characters or meaningless alone
│ └── Propose: reword with more context (store with replaces), or delete if worthless
│
└── No issues → skip
Skip memories created < 24 hours ago: too fresh to judge.
Step 3: Present action plan
Compile ALL proposals into one summary:
Hygiene report:
- 3 duplicate clusters: 8 memories → 3
- 2 contradictions: 1 replace, 1 needs your call
- 2 unscoped memories to re-scope
Approve all? Or review individually?
Wait for explicit approval. Do NOT execute anything until user approves.
Step 4: Execute approved changes
After user approves (all or specific items):
- Run each approved operation:
memory_store(..., replaces=<id>)for duplicates, corrections, re-scopingmemory_deleteonly for worthless entries (user explicitly approved)rekal prune --older-than-days N --yesfor approved bulk cleanup
- Report what was done, one line per action
- Run
rekal healthagain, report improvement:
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.
- 12d ago First seen · 107 lines · 77 tokens per session scan A 3705cb2426ab
rekal-hygiene is a skill published in the GitHub repository janbjorge/rekal (53 stars, last pushed 17d ago), licensed MIT. It adds 77 tokens to every session and 878 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
vault-for-llm
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
hmem-write
Hmem write protocol — picks prefix (L/E/D/P/N/R/I/H…), tree location, and tags, and detects duplicates before persisting. Use before any writememory or appendmemory call (skipping it creates duplicates and misplaced entries), or when the user says 'remember this', 'save this', 'log this', or invokes /hmem-write.
hmem-read
Load long-term memory from hmem via readmemory or loadproject. Use when starting fresh with no L1 summaries, after /compact, when the user asks 'what do you remember', 'continue where we left off', 'was war der letzte Stand', or about a project/topic visible in L1 summaries. Covers search, prefix filter, findrelated…
hmem-config
View and change hmem memory settings, hooks, sync, and checkpoints. Use on /hmem-config, or when the user asks why context is huge, how to change auto-save, how often checkpoints fire, or how to set up sync.
hmem-curate
Curate an .hmem file (your own or foreign) — mark obsolete/irrelevant, fix titles, consolidate duplicates, repair broken links. Requires the hmem-curate MCP server (skill prompts the user to enable it on entry). Use whenever the user says 'aufräumen', 'memory aufräumen', 'Speicher aufräumen', 'hmem aufräumen', 'clean…
hmem-session-start
Mandatory entry point for every Cortex session — invoke at conversation start, after /clear, and after any loadproject call. All stable context (H-entries, projects, device, sync) is pre-injected by the hook — no readmemory(mode='essentials') needed. Surfaces pending git work, Next Steps + open T-tasks, and runs the…