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.
git clone --depth 1 https://github.com/Shriniwas410/comcan-ctxWrote 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/rules/shriniwas410/comcan-ctx/comcan)<a href="https://agentmods.dev/rules/shriniwas410/comcan-ctx/comcan"><img src="https://agentmods.dev/badge/rules/shriniwas410/comcan-ctx/comcan/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/rules/shriniwas410/comcan-ctx/comcan"><img src="https://agentmods.dev/badge/rules/shriniwas410/comcan-ctx/comcan.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 | $0.00362 |
| Opus 5.5 | $0.00000 | $0.00145 |
| Sonnet 5.5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
comcan 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 2mo 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.
What it actually says
ComCan Agent Skill
You are operating in a repository powered by ComCan (Context Manager). ComCan provides you with a persistent, branch-aware "RAM" and "Hard Drive" so you don't have to guess project infrastructure.
1. Always Read the RAM First
Before writing code, you MUST read the current project state:
cat .comcan/CURRENT_STATE.md
This file tells you the current Git branch, recent commits, and a token-optimized directory tree.
2. Load the Hard Drive (Expertise)
If you are working on a specific domain (e.g., frontend, database, api), you MUST load the team's historical expertise before making architectural decisions:
comcan query <domain>
This will output JSONL or Text showing known rules, patterns, and past failures you must avoid.
3. Search for Unknowns
If you are unsure how to do something (e.g., "how do we handle auth?"), DO NOT guess. Search the expertise base:
comcan search "auth"
-
Read the Main Brain: Check for
ARCHITECTURE_MANIFESTO.mdin the repo root. If it exists, read it to understand the core architecture. If it's missing, suggestcomcan bootstrapto the user. -
Always Self-Onboard: Read
.comcan/CURRENT_STATE.mdto understand the branch state and directory structure. -
Pre-Flight Query: Before modifying a subsystem (e.g.,
api), runcomcan query apiin the terminal to load domain-specific rules. The CLI will handle formatting automatically.
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.
- 2mo ago First seen · 30 lines · 362 tokens per session scan A dc58f53b92b0
comcan is a cursor rule published in the GitHub repository Shriniwas410/comcan-ctx (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 362 tokens. 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 cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.