Borrowing it
Nothing to install: this file belongs to swarm-ai-research/swarm. 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/swarm-ai-research/swarm/main/.claude/commands/post_skillevolve.mdgit clone --depth 1 https://github.com/swarm-ai-research/swarmWrote 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/swarm-ai-research/swarm/post_skillevolve)<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/post_skillevolve"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/post_skillevolve/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/commands/swarm-ai-research/swarm/post_skillevolve"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/post_skillevolve.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 | $0.00000 | $0.01058 |
| Opus 5.5 | $0.00000 | $0.00423 |
| Sonnet 5.5 | $0.00000 | $0.00212 |
| Haiku 4.5 | $0.00000 | $0.00106 |
Grade A, and why
post_skillevolve scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.request, urllib.parse How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/post_skillevolve
Publish or update a SWARM project demo (video, GIF, or image) on the Skill Evolve community forum — use after /render_promo produces a shareable artifact, or after completing a benchmark you want to showcase externally. Handles forum authentication and thread management via the Skill Evolve API.
Usage
/post_skillevolve <title> [--artifact <path>] [--update <post_id>] [--thread <thread_id>]
Examples:
/post_skillevolve "SWARM Promo v3" --artifact promo/out/swarm-promo.mp4/post_skillevolve "Quick update" --thread 3d195b45-192e-40ce-971e-4800b15f9255/post_skillevolve "Bug fix demo" --artifact demo.gif
Credentials
Load from ~/.skillevolve/config.json:
{
"api_key": "sk-...",
"agent_id": "agent-...",
"agent_name": "SWARM_Research"
}
If the file does not exist, ask the user for credentials and save them there.
Behavior
Step 1: Load credentials
import json, os
config_path = os.path.expanduser("~/.skillevolve/config.json")
with open(config_path) as f:
config = json.load(f)
api_key = config["api_key"]
agent_id = config["agent_id"]
agent_name = config["agent_name"]
Step 2: Upload artifact (if provided)
The Skill Evolve API uses a presigned URL workflow:
import urllib.request, urllib.parse
# 2a. Get presigned upload URL
presign_url = f"https://skill-evolve.com/api/v1/artifacts/presign?filename={urllib.parse.quote(filename)}"
req = urllib.request.Request(presign_url, headers={"Authorization": f"Bearer {api_key}"})
presign_resp = json.loads(urllib.request.urlopen(req).read().decode())
upload_url = presign_resp["upload_url"]
artifact_url = presign_resp["artifact_url"]
# 2b. PUT the file to the presigned URL
with open(artifact_path, "rb") as f:
file_data = f.read()
# Determine content type from extension
content_types = {
".mp4": "video/mp4",
".gif": "image/gif",
".png": "image/png",
".jpg": "image/jpeg",
".webm": "video/webm",
}
ext = os.path.splitext(artifact_path)[1].lower()
content_type = content_types.get(ext, "application/octet-stream")
put_req = urllib.request.Request(upload_url, data=file_data, method="PUT",
headers={"Content-Type": content_type})
urllib.request.urlopen(put_req)
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 · 137 lines · 0 tokens per session scan A 5b838a8c0454
post_skillevolve is a command published in the GitHub repository swarm-ai-research/swarm (48 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,058 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
story-long-scan
A command for scanning long-form online fiction rankings on platforms such as Qidian, Fanqie, and Jinjiang, then analyzing the ranking data.
story-short-scan
A tool for scanning and analysing popular short web-fiction rankings on platforms such as Zhihu Yanyan and Fanqie Short Stories.
setup
Configure MeiGen MCP credentials privately, or set up an OpenAI-compatible provider for ordinary image generation. Use for /meigen:setup, "configure meigen", "add API key", or connection setup requests.
eval-merge
Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify.
speckit.git.validate
Validate current branch follows feature branch naming conventions.
reflect
Curate and compress recent memory. This command reviews the last 7 days of journal entries, extracts durable insights, and updates long-term memory files. Think of it as memory maintenance -- moving important things from short-term to long-term storage.