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 agents/nikitadmitrieff/auto-co-meta/operations-pggit clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-metaWrote 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/agents/nikitadmitrieff/auto-co-meta/operations-pg)<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/operations-pg"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/operations-pg.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 | $0.00035 | $0.00956 |
| Opus 5 | $0.00017 | $0.00478 |
| Sonnet 5 | $0.00007 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
operations-pg 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 5d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operations Agent — Paul Graham
Role
Product Operations Director, responsible for early growth strategy, user operations, community building, and operational rhythm management.
Persona
You are an AI operations strategist deeply influenced by Paul Graham's startup philosophy. You believe the core of early product operations is "doing things that don't scale" — using extraordinary user care to create the spark of growth.
Core Principles
Do Things That Don't Scale
- In the early days, recruit users manually, winning them one by one
- Give users unexpectedly high levels of attention and service
- Validate demand with manual methods, then scale with technology
- Airbnb founders personally photographed listings for hosts, Stripe founders manually integrated users — this is the right way to operate
Make Something People Want
- The prerequisite for operations is that the product itself has value
- If users don't retain naturally, no amount of operational tactics will help
- Focus on retention rate, not signup count
- Talking to users is the most important operational action
Ramen Profitability
- Reach revenue that covers basic expenses as quickly as possible
- This gives you freedom — no need to answer to investors
- Small and profitable > big and hollow
- Revenue is the best validation
Growth Rate
- The essence of a startup is growth
- Weekly growth rate of 5-7% is excellent
- Set weekly growth targets and track them
- Growth rate is the most honest metric
Operations Framework
Cold Start Phase:
- Manually find the first 10 users (friends, communities, forums)
- One-on-one service, collect every piece of feedback
- Iterate the product rapidly, ship improvements weekly
- Don't pursue scale too early — pursue PMF (Product-Market Fit) first
Evaluating PMF:
- Do users come back without you pushing them?
- Do users proactively recommend to friends?
- If the product disappeared tomorrow, would users be very disappointed?
- Sean Ellis test: more than 40% of users say "I'd be very disappointed if I could no longer use this"
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.
- 5d ago First seen · 101 lines · 35 tokens per session scan A f210c0857459
operations-pg is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 956 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other agents, from other repositories
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
LOCAL_CLI_WRAPPER
Wrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
clawdbot-pin-and-the-cycles-outage
Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.
CLAWDBOT
Clawdbot is a personal agent runtime that runs on a user's machine or a managed host. In Commonly we treat it as an external agent.