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/ohad6k/emulo/writenpx skills add ohad6k/emulo --skill writegit clone --depth 1 https://github.com/ohad6k/emuloWhat 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 | $0.00046 | $0.00417 |
| Opus 5 | $0.00023 | $0.00209 |
| Sonnet 5 | $0.00009 | $0.00083 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
write scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Emulo write
- Locate
emulo.pytwo directories above this skill; fall back to./emulo.pyonly for a direct repo checkout. - Store the resolved absolute runtime path as
EMULO_PY, then runpython "$EMULO_PY" plugin profile-path --domain write. - If it exits nonzero, give its exact recovery or targeted-deepen instruction and stop loading personal context.
- Read every returned path completely. The first is the core working profile; the second is the writing profile. Apply both.
- Pick the register from context; never ask. A writing profile with register sections (
## Voice laws,## Casual register,## Professional register) loads voice laws always, plus exactly one register:- An explicit audience statement from the user ("for my boss", "make it formal") always wins.
- Otherwise infer from what is in the task: a pasted thread with a manager, client, or customer, a formal email, documentation, or official product copy selects professional; a community reply, social post, chat banter, or a builder-to-builder thread selects casual; a pasted conversation selects the register matching that thread's own audience and tone.
- State the pick in one short line ("using professional register") so it is correctable, then write; never block on register confirmation.
- If the picked register has no section in the profile, load the voice laws only and never substitute the other register; say so in the same line ("professional register not mined yet, using voice laws only") and suggest
run emulo and deepen writeto mine it. - A flat profile without register sections applies in full, unchanged.
- Never imitate a generic voice when the writing domain is inactive.
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.
- 3d ago First seen · 19 lines · 46 tokens per session scan A 44f8bd8c0381
write is a skill published in the GitHub repository ohad6k/emulo (281 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 417 once invoked, about $0.0002 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
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
remove-meta-narrative
Detect and remove narration of the project's own history from published pages, so a reader gets the current state instead of a draft's changelog. Use before publishing or committing any edit to content/ or site/, when correcting a claim that turned out wrong, when folding a new finding into an existing page, and…
c-03-repo-bootstrap
Bootstrap onboarding for undocumented repos or existing memory slices. Builds root overviews, route-local overview pillars, evidence packs, file cards, onboarding waves, deleted-slice cleanup, curator reviews, and handoff while keeping the orchestrator thin.
c-12-closeout
Close out approved Agents Remember edits by preserving approval authority, mandatory strict code quality before code commit, missing-onboarding checks, external-memory refresh, memory quality, ledger alignment, and no automatic push.