Borrowing it
Nothing to install: this file belongs to P1-103n1x/bab-ilu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/P1-103n1x/bab-ilu/v2.2-oss-public/.claude/skills/evolve/SKILL.mdgit clone --depth 1 https://github.com/P1-103n1x/bab-iluWrote 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/p1-103n1x/bab-ilu/evolve)<a href="https://agentmods.dev/skills/p1-103n1x/bab-ilu/evolve"><img src="https://agentmods.dev/badge/skills/p1-103n1x/bab-ilu/evolve/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/p1-103n1x/bab-ilu/evolve"><img src="https://agentmods.dev/badge/skills/p1-103n1x/bab-ilu/evolve.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 | $0.00089 | $0.02681 |
| Opus 5.5 | $0.00036 | $0.01072 |
| Sonnet 5.5 | $0.00018 | $0.00536 |
| Haiku 4.5 | $0.00009 | $0.00268 |
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 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/evolve — Vault Self-Evolution
Philosophy
A vault that only accepts inputs is a passive file system. A self-evolving vault tells you what it should study next based on its own topology, bias, and authority-anchor health.
/evolve reads wiki/_insights.md (generated by tools/graph_analyzer.py) and turns its "content gaps" section into actionable work. Under the active lens, gaps are surfaced in lens-native vocabulary (aesthetic-warburg: Pathosformel / panel / authority anchor; engineering-alexander: pattern / force / incident; general-zettelkasten: concept-cluster / atomic-note).
v2.1 note — the gap-action playbooks below are currently v1.4-shaped around aesthetic-warburg semantics (Wikidata / Getty AAT / Warburg panel). Full lens-aware rerouting of the per-kind executors is tracked in ROADMAP as a Sprint 3+ target. Until then,
/evolveunder a non-aesthetic lens will surface gaps but defer execution to manual follow-up.
Invocation
/evolve # default: list top 3 gaps with suggestions
/evolve --list-all # list all gaps (can be dozens)
/evolve --take <N> # accept gap N and execute it automatically
/evolve --take <N> --dry-run # show what would happen without executing
/evolve --rebuild-insights # re-run tools/graph_analyzer.py before consulting
/evolve --priority high # filter by priority
/evolve --kind <kind> # filter by gap kind (missing_authority_anchor / underpopulated_domain / understaffed_panel / orphan_aesthetic / disconnected_clusters)
Execution flow
Step 1 — Ensure insights are fresh
If wiki/_insights.md is missing OR its updated: frontmatter is >7 days old, run python3 -m tools.graph_analyzer --vault <path> from the repo root first. (Both -m and the bare-script form work; -m is the canonical invocation — it is immune to PYTHONPATH surprises and matches how /lint --rebuild-graph spawns the analyzer internally.) Otherwise use existing.
Flag --rebuild-insights forces regeneration.
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 · 235 lines · 89 tokens per session scan A d14abb0fb544
evolve is a skill published in the GitHub repository P1-103n1x/bab-ilu (11 stars, last pushed 6mo ago), licensed MIT. It adds 89 tokens to every session and 2,681 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
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…