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-usagegit 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-usage)<a href="https://agentmods.dev/skills/janbjorge/rekal/rekal-usage"><img src="https://agentmods.dev/badge/skills/janbjorge/rekal/rekal-usage/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-usage"><img src="https://agentmods.dev/badge/skills/janbjorge/rekal/rekal-usage.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 | $0.00075 | $0.01138 |
| Opus 5.5 | $0.00030 | $0.00455 |
| Sonnet 5.5 | $0.00015 | $0.00228 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
rekal-usage 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 2mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have persistent memory via three rekal MCP tools. Follow these rules exactly.
The surface
| tool | purpose |
|---|---|
memory_build_context(query, project?, limit?, min_score?) |
recall: hybrid search over stored memories |
memory_store(content, project?, tags?, replaces?) |
persist one distilled fact; replaces=<old_id> updates an existing one |
memory_delete(memory_id) |
remove a memory that is wrong or obsolete |
Admin operations (health report, export, bulk prune) live in the CLI:
rekal health, rekal export, rekal prune.
Session start
Call memory_build_context(query="<task description>") before exploring the
codebase. Read the result before proceeding. Do this EVERY session.
Recalling
Queries go through hybrid search: BM25 keywords + vector similarity + recency
decay. Results below min_score (default 0.25) are dropped, so an empty
result means "nothing relevant", not "nothing stored".
Do: Use natural language with domain terms.
"JWT refresh token rotation policy": specific, has domain terms
"how to deploy auth service to staging": natural language, synonyms work
"user's preferred formatter and why": retrieves preferences with reasoning
Do not: Use vague, generic, or garbage queries.
"stuff": matches nothing useful
"code": matches everything
"the thing": no semantic content
project="backend": scope to one project. Use in multi-project workspaces.- Different angle on the same task = new
memory_build_contextcall with a reworded query.
Storing
Rule: ALWAYS recall before storing
1. memory_build_context(query="<what you want to store>")
2. Read results:
├── Exact duplicate found → do nothing
├── Same topic, outdated info → memory_store(content="...", replaces="<old_id>")
└── No match → memory_store(content="...", tags=[...])
Never skip step 1. Duplicates degrade search quality. Two memories about the
same topic must never coexist: replaces supersedes the old memory so it
stops surfacing in recall.
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.
- 2mo ago First seen · 123 lines · 75 tokens per session scan A 637eb4b24bda
rekal-usage is a skill published in the GitHub repository janbjorge/rekal (53 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 1,138 once invoked, about $0.0003 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 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.
misakanet-failure-memory
Search and record failure-recovery lessons from real engineering sessions; submit and verify debugging lessons across the MisakaNet network.
post-cortex-memory
Long-term project memory through the post-cortex MCP server (tools named session, semanticsearch, updateconversationcontext, assemblecontext, queryconversationcontext, getstructuredsummary, manageworkspace, manageentity, admin). Use it whenever those tools are available and the work could benefit from what was learned…
alice-memory
Use Alice as the user's durable local memory. Load before answering from context, and whenever you learn something worth keeping across sessions.
alice-project-memory
Use Alice as the project-scoped memory and continuity layer. Load before build or review work, and whenever a decision or constraint is worth keeping.
alice-correction-loop
Run deterministic correction workflows with Alice MCP review and correction tools, then verify that future outputs reflect the update.