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 ZekaiShi/evo-subagent --skill evo-memory-reviewgit clone --depth 1 https://github.com/ZekaiShi/evo-subagentWrote 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/zekaishi/evo-subagent/evo-memory-review)<a href="https://agentmods.dev/skills/zekaishi/evo-subagent/evo-memory-review"><img src="https://agentmods.dev/badge/skills/zekaishi/evo-subagent/evo-memory-review/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/zekaishi/evo-subagent/evo-memory-review"><img src="https://agentmods.dev/badge/skills/zekaishi/evo-subagent/evo-memory-review.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 | $0.00312 |
| Opus 5.5 | $0.00016 | $0.00125 |
| Sonnet 5 | $0.00008 | $0.00062 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
evo-memory-review 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 today.
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
Evo memory review
Review one workspace and one agent role at a time. The files are <workspace>/.evo_subagent/evolution/<agent_key>/prefercmd.md and memory.md; the main agent uses main as its key. The former .smart_subagent/evolution location can be a read-only fallback until the plugin migrates it.
- Compare each command with the workspace, operating system, tools, and available run evidence. Keep only commands actually shown to work; put reusable lessons or failure conditions in
memory.md. - Identify exact duplicates, conflicting advice, and entries tied to removed paths or versions. Treat
!as pinned and?as lower priority. Do not remove a pinned entry or turn an unverified guess into a verified command without evidence. - Present a compact keep/rewrite/remove proposal with reasons and the evidence used. If the user requested edits, make the smallest approved changes to these two files and preserve unrelated entries. Otherwise, stop at recommendations.
- After editing, reread both files and summarize the actual changes. Never add secrets, tokens, or raw private logs to evolution memory.
The plugin already bounds injected context and deduplicates new entries. This skill focuses on the quality of the stored knowledge, not on changing the plugin's storage rules.
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.
- today First seen · 16 lines · 41 tokens per session scan A 606ee7b1ca64
evo-memory-review is a skill published in the GitHub repository ZekaiShi/evo-subagent (7 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 312 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 2026-09-28.
Other skills, from other repositories
causal-memory
Causal memory for agents — install/setup the causal-memory MCP server, then record decisions/outcomes and recall them before acting. Trigger when the user asks to install or set up causal-memory/agent memory, when causal-memory MCP tools are available and the agent faces a non-trivial decision (architecture, debugging…
delivery-review
Adversarial self-review before delivery. Use once the implementation reaches green and before you declare the work done — assume the delivery fails its own spec, hunt for the strongest supportable objections, answer them, and re-review after fixes.
ito-compute
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô…
ito-inference
Inspect the availability of model serving on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed serving manifest. Use after ito-compute has booked GPU nodes and the user asks for an OpenAI-compatible endpoint, ito-serve, hosted Kimi, or self-hosted…
ito-training
Inspect the availability of ML training on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed training manifest. Use after ito-compute has booked GPU nodes and the user wants pre-training, fine-tuning, or RL on that metal. ECC implements no training…
code2skill-review-source
A read-only review skill for checking whether a Code2Skill-generated result matches the source code it was authorized to use. It examines request handling, tool handoffs, transformations, authentication, and attachments.