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 msinclair25/mdevolved --skill mdevolved-evegit clone --depth 1 https://github.com/msinclair25/mdevolvedWrote 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/msinclair25/mdevolved/mdevolved-eve)<a href="https://agentmods.dev/skills/msinclair25/mdevolved/mdevolved-eve"><img src="https://agentmods.dev/badge/skills/msinclair25/mdevolved/mdevolved-eve/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/msinclair25/mdevolved/mdevolved-eve"><img src="https://agentmods.dev/badge/skills/msinclair25/mdevolved/mdevolved-eve.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 | $0.00036 | $0.00526 |
| Opus 5.5 | $0.00014 | $0.00210 |
| Sonnet 5.5 | $0.00007 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
mdevolved-eve 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 1mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MDevolved + Eve
Use this pack only for Eve-side configuration. Eve owns sessions, channels, sandboxes, schedules, and child-agent runtime behavior. MDevolved owns the portable Project, owner approval, source boundary, packets, provenance, and cross-agent handoff.
Setup
- Add
agent/connections/mdevolved.tswith Eve's standarddefineMcpClientConnectionandconnect()helpers. - Use the deployment's HTTPS
/mcpURL andprincipalType: "user". - Request only the existing source-read and Project-initialization scopes. Keep credentials in Eve's connection store, never in prompts or files.
- Preserve every other connection and local agent instruction.
Eve qualifies the connection's tools as
mdevolved__connection_info, mdevolved__open_project,
mdevolved__wait_for_project_connection, and mdevolved__mdevolved_resume.
Top-level schedules cannot borrow a user's grant; route them through a
user-authenticated interaction or require explicit owner action.
Connect or resume
Read .mdevolvedignore first. If it is absent, read .owdignore as a legacy
fallback. If both exist and disagree, stop and ask the owner to resolve the
conflict. Never guess a Project or create a duplicate.
With a receipt, call mdevolved__mdevolved_resume first using its exact Project
UUID and context policy. Without one, call mdevolved__connection_info, then
mdevolved__open_project with the owner's visible Project name. For pending
approval, repeat only the same wait request and exact wait key. Until resume
returns localVaultAccess, the writer role is unconfirmed.
A new session, channel, or child reusing one connector UID is the same
MDevolved participant. Independent writers and reviewers need distinct
connector IDs and authorization. Before any deliberately mounted workspace or
source write, obey localVaultAccess; MCP submissions do not grant filesystem
authority.
Legacy compatibility
Existing pre-MD9 owd connections/tools and .owdignore receipts remain
readable. Preserve them and do not silently re-authorize or delete them; new
setup should use the canonical MDevolved connection and receipt names.
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.
- 1mo ago First seen · 51 lines · 36 tokens per session scan A f69d512d925f
mdevolved-eve is a skill published in the GitHub repository msinclair25/mdevolved (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 36 tokens to every session and 526 once invoked, about $0.0001 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 2026-09-01.
Other skills, from other repositories
triage-tasks
Use when you want to review and batch-update open vault task statuses for the current project or across all projects.
tackle-task
Use when starting work on a specific vault task, when a task title or path is mentioned, or when coming from triage output.
add-task
Use when you want to quickly capture a new task in the vault from a title, with optional priority and due date.
ariadne:workstream-tracking
Create, audit, or improve Obsidian Kanban work boards and Dataview dashboards for durable project, roadmap, evaluation, implementation, QA, or recurring workstream tracking inside an agent-maintained vault.
project-flow-ops
Use when projects or tasks need explicit state, WIP control, ownership, definitions of done, blocker handling, and verified closure.
pkm-session-end
Use when wrapping up a work session — creates devlog entry, captures undocumented decisions/research/debugging, audits link health of session work, and updates project index. Primarily used via the pkm-capture agent.