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 mubit-ai/claude-plugins --skill strategiesgit clone --depth 1 https://github.com/mubit-ai/claude-pluginsWrote 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/mubit-ai/claude-plugins/strategies)<a href="https://agentmods.dev/skills/mubit-ai/claude-plugins/strategies"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/strategies/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/mubit-ai/claude-plugins/strategies"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/strategies.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 | $0.00053 | $0.00737 |
| Opus 5 | $0.00026 | $0.00368 |
| Sonnet 5 | $0.00011 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
strategies 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 9d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call mubit_strategies — POST /v2/control/strategies — and report the strategies it returns
in the user's own terms: what the pattern is, and what it was inferred from. Ask for a small
number and report all of them; a wall of generalisations is less useful than three good ones.
The one thing to be clear about
mubit_strategies is the pattern across lessons. mubit_lessons reads the individual
lessons themselves.
Every other retrieval tool here answers with entries. mubit_recall finds the lessons that
match a question, mubit_lessons lists the catalogue, mubit_diagnose matches an error's
shape, mubit_dereference fetches the one whose reference_id you already hold. This is the
only one that answers with a shape over many of them: it clusters stored lessons into
emergent strategies, so what comes back is a generalisation the server derived, not a record
anybody wrote.
That makes the choice easy in both directions. "Why do we keep breaking the build the same
way?" and "what has this project learned about testing?" are strategy questions. "What did we
decide about the recall budget?" is not — that has one answer, and mubit_recall finds it
faster and quotes it. Do not reach for this tool to locate a single lesson; it will hand back
a summary of a cluster the lesson happens to sit in.
Arguments
max_strategies— 1 to 50. Ask for five to ten. The value of the answer is that it is short; fifty clusters over a few dozen lessons is the same information with the pattern taken back out.lesson_types— narrows which lessons get clustered, when the user is asking about one kind of thing ("what have we learned about failures?").session_idanduser_id— leave both out. The launcher already passes this run's id, anduser_idis a retrieval filter rather than a label: a value nothing was captured under matches nothing, so inventing one is how you get an empty answer from a full store.
Reporting it
A strategy is inferred, not stated. It has less standing than a rule, which somebody wrote
down on purpose and which is enforced as written. Say which you are relaying — presenting a
clustered generalisation as though the user had asked for it is how a plausible pattern
becomes a fact nobody agreed to.
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.
- 9d ago First seen · 52 lines · 53 tokens per session scan A 7442faf6cbd0
strategies is a skill published in the GitHub repository mubit-ai/claude-plugins (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 737 once invoked, about $0.0003 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.