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 skills/rekal-dev/rekal-cli/initnpx skills add rekal-dev/rekal-cli --skill initgit clone --depth 1 https://github.com/rekal-dev/rekal-cliWhat 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 | $0.00075 | $0.00550 |
| Opus 5 | $0.00037 | $0.00275 |
| Sonnet 5 | $0.00015 | $0.00110 |
| Haiku 4.5 | $0.00007 | $0.00055 |
Grade A, and why
init 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.
What it actually says
Initialize Rekal in this repository
Run once per repository. The binary must already be installed — if rekal is
not on PATH, use the install skill first.
Do not volunteer this
This skill is loaded in every repository the user opens. Almost none of them
should be initialized. Act when the user asks, or when a rekal command has
actually reported the repo is not initialized. A repository simply lacking
.rekal/ is not a reason to suggest anything.
Ask first
rekal init changes the user's repository. Name what it writes, then wait:
.rekal/— the store (two files: an append-onlydata.db, a localindex.db)- a
post-commit/pre-pushgit hook that captures sessions at commit time - an orphan branch
rekal/<their-email>used to transport memory over git - the full recall skill under
.claude/skills/rekal/ - one marker-tagged line in
CLAUDE.md, plus the equivalent line in any other agent rules file it detects (AGENTS.md,GEMINI.md,.github/copilot-instructions.md,.kiro/steering/rekal.md)
User content is never rewritten — only the marker line is added. rekal clean
removes everything, with no residue.
If the user declines, stop and say so plainly.
Run it
From the repository root:
rekal init
After
Say what to expect, because the first impression is misleading:
- A fresh store is empty. Recall stays silent until the next commit. That silence is correct, not a broken install — memory accumulates from here.
- If the team already shares a ledger,
rekal syncpulls it now and recall has something to find immediately.
From this point the binary owns memory. It installed the full recall skill, which is the one that answers questions — richer than anything in this plugin, and versioned with the binary whose commands it runs. Route recall questions there. This skill is done until the next repository.
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 · 61 lines · 75 tokens per session scan A a0f6700ecef9
init is a skill published in the GitHub repository rekal-dev/rekal-cli (140 stars, last pushed 28d ago), licensed Apache-2.0. It adds 75 tokens to every session and 550 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
video
Use when a brief has to become a film. Turns a one line ask into a Claude Design prompt written in the animations-v3 engine's own language, plus the built piece.jsx and a contact sheet to look at before anyone renders. Covers reference roles, the kit, the storyboard gate, the motion floor, and the verification…
emulo
Use when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history and native emulo:mine is not available. This is the cross-agent skills.sh bootstrap, not the native namespaced plugin.
emulo
Load the user's Emulo profile, mined from their local Claude Code, Codex, and OpenCode session logs, so you work like them instead of a cold start. Use before working on their task.
mine
Use only when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history.
write
Use for marketing, social, replies, product copy, launch copy, and writing in the user's voice when their Emulo writing profile should guide the task. Do not use for unrelated execution or UI/UX design alone.
design
Use for UI, UX, visual hierarchy, frontend-design judgment, references, redesigns, and design critique when the user's Emulo taste should guide the task. Do not use for unrelated execution or marketing/social writing alone.