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 skills/haseebkhalid1507/synapscli/extension-authoringnpx skills add HaseebKhalid1507/SynapsCLI --skill extension-authoringgit clone --depth 1 https://github.com/HaseebKhalid1507/SynapsCLIWrote 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/haseebkhalid1507/synapscli/extension-authoring)<a href="https://agentmods.dev/skills/haseebkhalid1507/synapscli/extension-authoring"><img src="https://agentmods.dev/badge/skills/haseebkhalid1507/synapscli/extension-authoring.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 | $0.00034 | $0.01609 |
| Opus 5 | $0.00017 | $0.00805 |
| Sonnet 5 | $0.00007 | $0.00322 |
| Haiku 4.5 | $0.00003 | $0.00161 |
Grade A, and why
extension-authoring 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 4d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
proc = subprocess.Popen(["python3", "main.py"], How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a SynapsCLI Extension
Source of truth:
{baseDir}/../../../docs/extensions/tutorial.mdRead that file for the complete worked example. This skill is a structured summary + checklist you can keep in context while authoring.
What you are building
A separate process SynapsCLI spawns and talks to over stdin/stdout using
JSON-RPC 2.0 with Content-Length framing. The runtime calls methods on
you; you only respond. Any language works — Python 3 (no deps) is the tutorial
language.
Two capabilities:
- Tool — callable by the model (
tools.registerpermission required). - Hook — reacts to lifecycle events, optionally blocks/modifies them
(
hook.*permission required per hook type).
Step 1 — Manifest (plugin.json)
Create .synaps-plugin/plugin.json in your extension root:
{
"name": "hello-ext",
"version": "0.1.0",
"description": "Hello-world extension",
"extension": {
"entry_point": "python3 main.py",
"extension_protocol_version": 1,
"permissions": [
"tools.register",
"hooks.before_tool_call"
]
}
}
Key fields:
entry_point— shell command to start your process (resolved from plugin root).extension_protocol_version— must be1.permissions— declare every capability you use; undeclared calls are rejected.
Step 2 — Framing helpers
Every message is a Content-Length: N\r\n\r\n header followed by N bytes of
JSON. Write helpers once:
import sys, json
def send(obj):
body = json.dumps(obj).encode()
sys.stdout.buffer.write(b"Content-Length: " + str(len(body)).encode() + b"\r\n\r\n" + body)
sys.stdout.buffer.flush()
def recv():
header = b""
while not header.endswith(b"\r\n\r\n"):
header += sys.stdin.buffer.read(1)
n = int(header.split(b"Content-Length:")[1].strip().split()[0])
return json.loads(sys.stdin.buffer.read(n))
Step 3 — Handshake (initialize)
The runtime sends initialize first. You must respond with your capabilities:
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.
- 4d ago First seen · 240 lines · 34 tokens per session scan A 61f39a30e4ed
extension-authoring is a skill published in the GitHub repository HaseebKhalid1507/SynapsCLI (40 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 1,609 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…