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 skills add Vladick-Pick/business-ontology --skill interaction-contractgit clone --depth 1 https://github.com/Vladick-Pick/business-ontologyWrote 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/vladick-pick/business-ontology/interaction-contract)<a href="https://agentmods.dev/skills/vladick-pick/business-ontology/interaction-contract"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/interaction-contract/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/skills/vladick-pick/business-ontology/interaction-contract"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/interaction-contract.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 | $0.00037 | $0.01202 |
| Opus 5.5 | $0.00015 | $0.00481 |
| Sonnet 5.5 | $0.00007 | $0.00240 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
interaction-contract 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interaction contract
Purpose
Use this skill to configure one owner reminder independently from the silent system heartbeat. This is agent runtime configuration, not part of the company model.
When to use
Use this skill:
- during Block C of first-session onboarding;
- when the owner says "let's do weekly", "come every morning", or similar;
- when a workspace is missing
INTERACTION_CONTRACT.md; - after a host migration that requires cron jobs to be recreated.
Do not use propose-change for this. The interaction contract lives in the
private agent workspace and changes by explicit owner instruction.
Controls
The two controls never substitute for each other:
- the 2h heartbeat silently refreshes system health and has no delivery target;
- one declaration-keyed cron reminds the owner only on the confirmed schedule.
Recommend a daily reminder at 09:00 in the owner's IANA timezone, in the owner-controlled Telegram DM, with a 22:00-09:00 quiet window. Weekly or another cadence is valid when the owner chooses it.
Procedure
- Keep the explicit per-agent 2h heartbeat unchanged.
- Read
owner_reminder.setup_statusfromagent-state/managed-scheduling.json. In an owner-controlled interactive turn,needs-owner-questionmeans this resident agent records onehuman_requestwithkind=setup, changes the status toawaiting-owner, and asks one question for cadence/time, IANA timezone, channel, quiet window, and language. Include one recommended complete answer and its consequence. Do not ask from heartbeat or another scheduled run, and do not repeat the question while the status isawaiting-ownerordeferred. - Accept the profile only from an owner-controlled channel. Correlate an exact reply before changing runtime state.
- Update
agent-state/managed-scheduling.jsonand the human-readableINTERACTION_CONTRACT.md, setsetup_status=configured, and clearrequires_owner_confirmation. Store the confirmation message reference and timestamp, not the reply body. - The resident agent itself converges the one declaration-keyed OpenClaw
command cron using its host scheduling tool and
adapters/openclaw/SCHEDULING.md. The package installer or host operator does not create this owner-specific job while that tool is available. - Verify the actual cron and run one empty/non-empty reminder smoke.
- Reply with one mirror line.
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 · 126 lines · 37 tokens per session scan A f6d4e2b12d9c
interaction-contract is a skill published in the GitHub repository Vladick-Pick/business-ontology (3 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,202 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
interaction-contract compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| interaction-contractVladick-Pick/business-ontology | Skill | 3 | 3mo ago | MIT | A | 37 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |