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 CocoRoF/geny-executor --skill environmentgit clone --depth 1 https://github.com/CocoRoF/geny-executorWrote 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/cocorof/geny-executor/environment)<a href="https://agentmods.dev/skills/cocorof/geny-executor/environment"><img src="https://agentmods.dev/badge/skills/cocorof/geny-executor/environment/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/cocorof/geny-executor/environment"><img src="https://agentmods.dev/badge/skills/cocorof/geny-executor/environment.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 | $0.00065 | $0.01028 |
| Opus 5.5 | $0.00026 | $0.00411 |
| Sonnet 5.5 | $0.00013 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
Self-Modifying Environment 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editing your own environment
You can change your own operating environment with the env tool. Changes
are session-scoped (they affect only you, not other sessions or the shared
template) and take effect from the next turn. Every change is logged.
env takes an action and an args object. Always start with
env(action="view") to see what's active vs available before editing.
Quick recipes
- See your environment —
env(action="view"). Returns your prompt size, active vs available tools, active vs available skills, and change count. - Read your prompt —
env(action="get_prompt"). - Rewrite your prompt —
env(action="set_prompt", args={"prompt": "<full new prompt>"}). Replaces it entirely; read it first. Useappend_promptto add a section instead of replacing. - Add a section to your prompt —
env(action="append_prompt", args={"text": "..."}). - Turn a tool on —
env(action="enable_tool", args={"name": "<tool>"}). Only tools shown underavailable_toolsinviewcan be enabled. - Turn a tool off —
env(action="disable_tool", args={"name": "<tool>"}). - Turn a skill on/off —
env(action="enable_skill", args={"skill_id": "<id>"})/env(action="disable_skill", args={"skill_id": "<id>"}). - Author a reusable skill —
env(action="create_skill", args={"skill_id": "...", "description": "one line — when to use it", "body": "# Title\n\nstep-by-step instructions"}). It is enabled immediately. Edit later withenv(action="edit_skill", args={"skill_id": "...", "body": "..."}). - Inspect tool settings —
env(action="get_settings"). Shows the configurable values tools need (e.g. a search backend + API key); secrets are masked.args.schemasdescribes what each group accepts when the host declares it. - Set a tool's value (API key, backend, URL, …) —
env(action="set_setting", args={"key": "web_search", "field": "brave_api_key", "value": "..."}). Takes effect on the next call of that tool. - Inspect tunable config —
env(action="get_config"). Model knobs (temperature, max_tokens, thinking…) + pipeline limits (max_iterations); plus the LOCKED core (model, provider) you cannot change. - Set a config knob —
env(action="set_config", args={"key": "temperature", "value": 0.7}). Takes effect next turn. Core keys (model/provider) are refused. - Review your changes —
env(action="changelog"). - Save —
env(action="save"). Persists your evolved environment for THIS session so it is restored next time. (If saving isn't configured the call reports that and your changes simply stay live for this session.)
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 · 69 lines · 65 tokens per session scan A 5b1f493bbf95
Self-Modifying Environment is a skill published in the GitHub repository CocoRoF/geny-executor (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,028 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
skill-creator
Create new reusable skills from conversation context.
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
continuum-handoffs
Build agent-to-agent transitions with Continuum's Handoff system — triage routing, history summarization modes (FULL/SUMMARY/RECENTN/HYBRID), cycle detection, depth tracking, return-to-parent. Invoke when the user asks "route customer requests to specialists", "agent that can transfer to another", "summarize history…
continuum-llm-providers
Pick the right LLM provider, configure structured outputs, control context-window compression, and use the LLMClient directly. Provider routing is by model-string prefix; LiteLLM has been removed. Also covers Smart Gateway integration for multi-provider routing. Invoke when the user asks about "switch to Claude"…
continuum-observability
Trace agent runs with Langfuse, decorate functions with @observe, collect latency/token/error metrics, and report errors. Invoke when the user asks about "see what the LLM was prompted with", "Langfuse traces", "track latency", "metrics dashboard", "error reporting", or "instrument my function".
continuum-temporal
Build durable agent workflows with Temporal — sequential/parallel/loop/conditional steps, human-in-the-loop approval gates, custom workflows and activities. Invoke when the user asks "long-running workflow", "approval gate", "human in the loop", "retry on failure", "workflow survives restart", or anything…