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 RikyZ90/ShibaClaw --skill evolvegit clone --depth 1 https://github.com/RikyZ90/ShibaClawWrote 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/rikyz90/shibaclaw/evolve)<a href="https://agentmods.dev/skills/rikyz90/shibaclaw/evolve"><img src="https://agentmods.dev/badge/skills/rikyz90/shibaclaw/evolve/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/rikyz90/shibaclaw/evolve"><img src="https://agentmods.dev/badge/skills/rikyz90/shibaclaw/evolve.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 | $0.00041 | $0.00968 |
| Opus 5.5 | $0.00016 | $0.00387 |
| Sonnet 5.5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
evolve 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 yesterday.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolve
One alarm tick. Do not edit this skill to skip the gate. Do not commit the default branch. Do not push or force-push main or master. Do not change the model provider. Do not ask the owner between steps. Push evolve/* only to the fork remote and open the pull request on the fork. VERDICT: PASS does not authorize a merge. Merge that fork pull request only after shibaclaw evolve check prints evolve check ok. Never open or merge a pull request against upstream.
State: shibaclaw evolve (on|off|status|panic|gate|end|note-apply|check).
Review checklist: the evolve CHECKLIST.md next to this file.
0. Gate
shibaclaw evolve gate
Non-zero → reply exactly EVOLVE_SKIP and stop.
1. Fuel
Read memory/knowledge/patterns.md, memory/knowledge/improvement-backlog.md, and the tail of memory/DREAM_DIARY.md.
The same failure twice, and the class is not in patterns yet → append the class and one Open backlog item. Then shibaclaw evolve end. Tell the owner one line. Stop.
An Open item exists → take the top one through review or FAIL. Nothing open and no new class → do not stop. One world topic, section 5.
2. Branch
Dirty tree, or checkout -b evolve/<slug> failed → shibaclaw evolve end and stop.
<slug> is the class name: letters, digits, hyphen.
Touch only that class. Do not touch secrets, .env, credentials, or the owner allowlist.
Commit on evolve/<slug> only. Do not push yet. NOT_RUN does not skip tests.
3. Reviewer
A different model on the same provider. Do not write config.
shibaclaw agent --session evolve:reviewer --model <reviewer-model> --no-markdown --logs "Read the evolve CHECKLIST.md. Read git diff <default>...HEAD. Read-only: do not edit, commit, push, or apply. Last line exactly VERDICT: PASS or VERDICT: FAIL."
No VERDICT: PASS line → record FAIL, leave the item Open, shibaclaw evolve end, one line to the owner. The next alarm may take the next item.
4. Check
Push evolve/<slug> to the fork only. Open the pull request on the fork. Never push the default branch.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +5 lines 330f841ee498
- 9d ago First seen · 68 lines · 41 tokens per session scan A 05795430b011
evolve is a skill published in the GitHub repository RikyZ90/ShibaClaw (82 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 968 once invoked, about $0.0002 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 2026-10-09.
Other skills, from other repositories
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
mem0-integrate
Integrate Mem0 into an existing repository using a goal-driven, TDD pipeline. Detects the repo's language automatically and asks the user to pick between Mem0 Platform (managed) and Mem0 Open Source (self-hosted). Writes failing tests before any implementation. Produces a local feature branch plus .mem0-integration/…
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.
agent-tool
Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's capabilities, wiring a new function into the agent, or when the model needs a new action. This project uses {{ cookiecutter.aiframework }}.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
rag-knowledge
Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…