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 commands/michael-ovo/obsidian-knowledge-agent/evolvegit clone --depth 1 https://github.com/Michael-OvO/obsidian-knowledge-agentWrote 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/commands/michael-ovo/obsidian-knowledge-agent/evolve)<a href="https://agentmods.dev/commands/michael-ovo/obsidian-knowledge-agent/evolve"><img src="https://agentmods.dev/badge/commands/michael-ovo/obsidian-knowledge-agent/evolve.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00210 |
| Opus 5 | $0.00006 | $0.00105 |
| Sonnet 5 | $0.00003 | $0.00042 |
| Haiku 4.5 | $0.00001 | $0.00021 |
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 3d 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.
What it actually says
Show me the pending self-evolution changes and walk me through approving them.
- Run
git --no-pager diff -- .agents/learned/to surface proposed changes toconventions.md,examples.md, andskills/. - For each change, summarize it in one line and cite the
journal.mdentry that motivated it (read the latest entries for context). - Check it against rule precedence in
.agents/self-evolution.md: a learned rule must not contradict a core rule in.agents/*.mdor the user's stated preferences. Flag any that do. - For each: ask whether to keep, edit, or discard.
- Commit approved changes with
chore(learn): <one-line summary>. Revert discarded ones (git checkout -- <path>). Leave the journal untouched — it is the record.
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.
- 3d ago First seen · 17 lines · 13 tokens per session scan A 64fd6687c5bf
evolve is a command published in the GitHub repository Michael-OvO/obsidian-knowledge-agent (207 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 210 once invoked, about $0.0001 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 commands, from other repositories
design
Early-stage design exploration — settle the shape of a feature/recipe/system before scoping its implementation. Re-entrant; agent-judged writes.
scope
Project-level scoping — refine a single living vault note for a project, with mandatory unknowns tracking. Re-entrant; agent-judged writes.
decompose
Feature/story breakdown — consume a ready-for-decompose scope doc and produce a task graph in the issue tracker. Re-entrant; tracker-as-canonical with vault breadcrumb.
implement
Feature implementation in a repo — ticket → plan gate → develop-to-plan → draft-PR review loop (human gate) → squash-clean finalize. Thin recipe over six overridable primitives; dossier-mcp the only hard dependency.
research
Conversation-shaped research loop — vault grounding + web research + agent-judged capture (no pre-write sign-off).
dossier
Force load of Dossier vault profile (and inbox check) before processing the rest of the user's request.