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/fmarzochi/egc/evolvegit clone --depth 1 https://github.com/Fmarzochi/EGCWrote 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/fmarzochi/egc/evolve)<a href="https://agentmods.dev/commands/fmarzochi/egc/evolve"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/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 | $0.00008 | $0.00243 |
| Opus 5 | $0.00004 | $0.00121 |
| Sonnet 5 | $0.00002 | $0.00049 |
| Haiku 4.5 | $0.00001 | $0.00024 |
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 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
Evolve Command
Analyze and evolve instincts in continuous-learning-v2: $ARGUMENTS
Your Task
Run:
python3 "${GEMINI_PLUGIN_ROOT}/skills/continuous-learning-v2/scripts/instinct-cli.py" evolve $ARGUMENTS
If GEMINI_PLUGIN_ROOT is unavailable, use:
python3 ~/.gemini/skills/continuous-learning-v2/scripts/instinct-cli.py evolve $ARGUMENTS
Supported Args (v2.1)
- no args: analysis only
--generate: also generate files underevolved/{skills,commands,agents}
Behavior Notes
- Uses project + global instincts for analysis.
- Shows skill/command/agent candidates from trigger and domain clustering.
- Shows project -> global promotion candidates.
- With
--generate, output path is:- project context:
~/.gemini/homunculus/projects/<project-id>/evolved/ - global fallback:
~/.gemini/homunculus/evolved/
- project context:
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 · 37 lines · 8 tokens per session scan A fc7c0369a6b9
evolve is a command published in the GitHub repository Fmarzochi/EGC (48 stars, last pushed today), licensed Apache-2.0. It adds 8 tokens to every session and 243 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
session-list
List recent sessions from the project ledger and offer to view one.
session-start
Start recording this agent session to the project ledger.
decisions
Complete reference for managing architectural decision records (ADRs).
telemetry
Complete reference for telemetry consent management commands.
worker
Complete reference for worker identity and configuration commands.
ox-session-recover
Command "ox-session-recover" from sageox/ox, covering recovery flow, step 1: find the claude code transcript, step 2: try the built-in recover command first, step 3: convert transcript to web viewer format and step 4: lint the converted jsonl.