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 instructions/solidkeyab/logan/copilot-instructionsgit clone --depth 1 https://github.com/SolidKeyAB/loganWhat 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 | $0.00872 | $0.00872 |
| Opus 5 | $0.00436 | $0.00436 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
logan copilot-instructions.md 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 2d 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, json, time How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LOGAN — Copilot Agent Instructions
LOGAN is an Electron log analysis tool running locally with an HTTP API for agent communication.
Connecting to LOGAN
API base: http://127.0.0.1:19532
Check if LOGAN is running and a file is open:
GET /api/status
→ {"success": true, "status": {"filePath": "...", "totalLines": 14957, ...}}
Chat with the User
LOGAN has a Chat panel where the user can see your messages and reply.
Register as connected (shows green dot in LOGAN, call once on start):
POST /api/agent-register
Content-Type: application/json
{"name": "Copilot"}
Send a message (also refreshes your connected status):
POST /api/agent-message
Content-Type: application/json
{"message": "Hello from Copilot!", "name": "Copilot"}
Poll for user replies (every 2-3 seconds):
GET /api/messages?since=<timestamp_ms>
→ {"messages": [{"from": "user", "text": "hi!", "timestamp": 1234567890}]}
Filter for "from": "user" messages only (ignore your own "from": "agent" messages).
Chat Loop (Python)
import urllib.request, json, time
API = "http://127.0.0.1:19532"
last_ts = int(time.time() * 1000)
def send(text):
data = json.dumps({"message": text}).encode()
req = urllib.request.Request(f"{API}/api/agent-message", data=data,
headers={"Content-Type": "application/json"}, method="POST")
urllib.request.urlopen(req)
def poll(since):
req = urllib.request.Request(f"{API}/api/messages?since={since}")
resp = urllib.request.urlopen(req)
return [m for m in json.loads(resp.read()).get("messages", []) if m["from"] == "user"]
send("Hello! I'm connected to LOGAN.")
while True:
time.sleep(2)
for msg in poll(last_ts):
last_ts = msg["timestamp"]
if "goodbye" in msg["text"].lower():
send("Goodbye!")
exit()
send(f"Got it: {msg['text']}")
Log Analysis Endpoints
| Action | Method | Endpoint | Body |
|---|---|---|---|
| Register agent | POST | /api/agent-register | {"name": "Copilot"} |
| Get status | GET | /api/status | — |
| Open file | POST | /api/open-file | {"filePath": "/path/to/file"} |
| Get lines | GET | /api/lines?start=0&count=10 | — |
| Search | POST | /api/search | {"pattern": "ERROR", "maxResults": 50} |
| Analyze | POST | /api/analyze | — |
| Navigate | POST | /api/navigate | {"line": 123} |
| Filter | POST | /api/filter | {"pattern": "ERROR"} |
| Clear filter | POST | /api/clear-filter | — |
| Bookmarks | GET | /api/bookmarks | — |
| Add bookmark | POST | /api/add-bookmark | {"line": 123, "label": "crash"} |
| Highlights | GET | /api/highlights | — |
| Add highlight | POST | /api/add-highlight | {"pattern": "ERROR", "color": "#ff0000"} |
| Time gaps | POST | /api/time-gaps | — |
| Baselines | GET | /api/baselines | — |
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.
- 2d ago First seen · 96 lines · 872 tokens per session scan A 4bab88657bad
logan copilot-instructions.md is an instructions file published in the GitHub repository SolidKeyAB/logan (4 stars, last pushed 5d ago), licensed MIT. It adds 872 tokens to every session, about $0.0044 per session on Opus 5. 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 2026-08-31.
Other instructions, from other repositories
outline-apps AGENTS.md
AGENTS.md instructions for OutlineFoundation/outline-apps, covering welcome to the outline monorepo!, repository structure, the npm run action command, common actions and other useful commands.
outline-apps CLAUDE.md
Claude Code instructions for OutlineFoundation/outline-apps: This project uses AGENTS.md instead of CLAUDE.md.
clave CLAUDE.md
Instructions for codika-io/clave, covering clave, commands, architecture, conventions and signing and notarization.
itsyconnect-macos CLAUDE.md
Instructions for nickustinov/itsyconnect-macos, covering itsyconnect – llm build guide, required reading, project rules, core principles and routing and request interception.
snip CLAUDE.md
Instructions for rixinhahaha/snip, covering claude.md — autonomous agent instructions, role documents, documentation rules, how to update and critical constraints.
pin-it-public AGENTS.md
Instructions for johnnyzhoujz/pin-it-public, covering pin it repository guidance, working practices and packaged-app testing.