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 SoliEstre/EstreGenesis --skill subscalergit clone --depth 1 https://github.com/SoliEstre/EstreGenesisWrote 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/soliestre/estregenesis/subscaler)<a href="https://agentmods.dev/skills/soliestre/estregenesis/subscaler"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/subscaler/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/soliestre/estregenesis/subscaler"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/subscaler.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 | $0.00145 | $0.04788 |
| Opus 5.5 | $0.00058 | $0.01915 |
| Sonnet 5.5 | $0.00029 | $0.00958 |
| Haiku 4.5 | $0.00015 | $0.00479 |
Grade A, and why
subscaler 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 19d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/subscaler — tiered model composition
/superscalar decides how eagerly to fan out. This skill decides what each lane runs on — tier and effort. The two are orthogonal; set them independently.
The mechanism that makes a tier drop safe is spec completion before offload: a fully-specified lane loses little from one tier down, an underspecified one loses a lot. Spec completeness is the quality moderator, not model size.
Toggle contract
- State = one marker file:
.agent/subscaler.json—{"on": true, "family": "<vendor>", "effort": "<level>"}. Read at invocation time; never mirror the state into other settings surfaces (duplicated per-role model bindings have shipped state-convergence bugs). /subscaler onwrites it ·/subscaler offremoves it (or sets"on": false) ·/subscaler statusreads it back and reports where it would apply next.- Default OFF. ON is recommended where fan-out has already forfeited the shared prompt cache. A delegated subagent starts cache-cold on its own model, so a small, cache-hot, deep-context edit loses money on delegation.
Step 0 — frontier-main cost gate (when the orchestrator itself is T1)
If the main conversation runs on a T1 model (a Fable-class flagship), inheritance is the failure mode: the Agent tool resolves a subagent's model as per-invocation model → frontmatter model → CLAUDE_CODE_SUBAGENT_MODEL (a default, not a pin, since v2.1.251 — before that the env var came first) → the main model, and a Workflow agent() that omits opts.model inherits the same way. Nothing in that chain says "frontier" — it just is. Two env facts sit outside the chain: CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1 (v2.1.257+) overrides every binding including the ones you wrote, and under a Fable main the built-in Explore agent's model depends on the connection — with a Claude subscription, a Console account or an ANTHROPIC_BASE_URL gateway it runs on whatever the opus alias resolves to (currently Opus 5.5), on other providers it stays on the main model (registry harnessBinding) — neither is visible from the spawn request, so verify with /tasks (v2.1.242+), which names each running subagent's model and effort. And every unbound lane inherits the session's effort level; ultracode is not a level — since v2.1.284 it is a toggle that stays on at whatever level the session runs (only --effort ultracode also sets xhigh). So, before any fan-out on a T1 main:
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.
- 19d ago Changed · +13 lines 929ce68b126b
- 21d ago Changed f25357cd98db
- 29d ago Changed · +2 lines 3951954ba606
- 1mo ago Changed · +11 lines 34db975f70a1
- 1mo ago First seen · 87 lines · 145 tokens per session scan A 2c6974553528
subscaler is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 145 tokens to every session and 4,788 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
agentic-delivery-playbook
Apply the maintained Agentic Delivery Playbook in Pi: classify work as Direct or Controlled, choose the minimum safe route, and close from evidence. Use for coding work when explicit scope, risk, route, or validation guidance will improve the next action.
agentic-delivery-playbook
Use for non-trivial coding work that benefits from a spec-gated delivery workflow: features, refactors, integrations, workflow changes, bug fixes with ambiguity, safety/privacy/security risk, cross-package changes, public contract changes, or agent drift risk. Do not use for clear small direct edits unless the user…
ppgp
Portable Persistent Goal Protocol for long-running coding-agent work. Use when starting, resuming, handing off, distilling, or closing a substantial software goal across long sessions, context compaction, agent replacement, or other Agent Skills-compatible coding-agent environments.
update-agent-context
This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…
watercooler-onboarding
Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…
search-threads
Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.