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 agentmods add skills/msinclair25/mdevolved/owd-evenpx skills add msinclair25/mdevolved --skill owd-evegit clone --depth 1 https://github.com/msinclair25/mdevolvedWhat 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 | $0.00090 | $0.01408 |
| Opus 5 | $0.00045 | $0.00704 |
| Sonnet 5 | $0.00018 | $0.00282 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade A, and why
owd-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 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MDevolved + Eve
Legacy compatibility path. New setups should use
mdevolved-eve; keep this pack for existingowdconnections and receipts.
Keep one universal MDevolved server. Apply this profile as Eve-side configuration and instructions; never change MCP framing, OAuth, tool schemas, or MDevolved authority for Eve.
Confirm the runtime
- Confirm the repository uses Eve and has an
agent/directory. - Read the repository's
AGENTS.mdand local agent instructions. - Add
agent/connections/owd.ts; its filename makes the Eve connection nameowd. - Use
defineMcpClientConnectionwith the deployment's standard remote Streamable HTTP/mcpURL. - Use
connect()from@vercel/connect/evewithprincipalType: "user",autoProvision: true, the MDevolved MCP URL as the token resource, and only these source-grant scopes:vault.read,project.initialize.request, andproject.connect.request.
Do not add a proxy, static bearer token, app principal, custom tool schema, client-side Project authority, or a second MDevolved endpoint. Do not pin a local tool allowlist: MDevolved's advertised catalog and server-side grant remain authoritative.
Eve 0.29.4 can install integrations from its registry with eve add or
interactive /add. MDevolved is not represented as registry-installed until Eve's
upstream registry accepts it. Until then, use the generated
agent/connections/owd.ts module from the MDevolved dashboard; do not claim that
eve add owd is available.
Authenticate in the right context
Eve's user-scoped connection requires a signed-in user route. Let Eve pause the tool call, open its connection flow, and resume after the owner approves the exact MDevolved vault and folder boundary. Credentials stay in Vercel Connect rather than model-visible history.
If Eve reports principal_required, use a user-authenticated Eve route. This
is not an MDevolved revocation and is not repaired by reconnecting MDevolved or changing to
principalType: "app".
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 First seen · 128 lines · 90 tokens per session scan A 234b68f36dd9
owd-eve is a skill published in the GitHub repository msinclair25/mdevolved (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 1,408 once invoked, about $0.0005 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 2026-09-01.
Other skills, from other repositories
audit-share
Batch-review personal knowledge for promotion to team-shared project knowledge. Walks insights/decisions/approaches/rules and IDEAS-BACKLOG.md entries, recommends a target project-knowledge/ destination per item, and lets the user approve all/numbers/modify/skip. Use when user says '/audit-share', '/share-audit'…
intake
Capture knowledge from outside the conversation. A single URL or text snippet is clipped whole to intake/clippings/; files/directories/globs are bulk-scanned into the backlogs; extract decomposes a source into backlog entries; doc captures a structured 5-section reflection…
audit-rules
Mine your distilled knowledge corpus — memory feedback rows, rules backlogs, always-on indexes — for recurring corrections that deserve promotion to numbered standing rules. Clusters by theme, verifies every quote at its source file, ranks by cross-session recurrence (>=2 distinct sessions), and writes a rule ONLY on…
audit
Umbrella for the audit family. Routes to the sub-audits: knowledge (backlog→knowledge promotion), config (CLAUDE.md/settings drift), style (mine session-log history for revealed working-style rules), and usage (value/ROI report for your own corpus). Use '/audit' for a menu, or '/audit knowledge|config|style|usage|all'…
stats
Show knowledge base health metrics — file counts, backlog depth, audit status, codemap dates, tag stats, and coverage gaps. Use when user says '/stats', 'knowledge stats', 'how is my knowledge base', 'show stats', 'knowledge health', 'dashboard'. (Code port — ADR-094.).
ask
Research a question, check existing knowledge first, draft a knowledge doc from the answer, and save directly to the appropriate category. Use when user says '/ask', 'ask about', 'research and save', 'I want to learn about', 'what is the pattern for'. Skips backlogs — the user reviews the answer in real-time before…