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/datacore-one/datacore-mcp/datacore-v2npx skills add datacore-one/datacore-mcp --skill datacore-v2git clone --depth 1 https://github.com/datacore-one/datacore-mcpWrote 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/datacore-one/datacore-mcp/datacore-v2)<a href="https://agentmods.dev/skills/datacore-one/datacore-mcp/datacore-v2"><img src="https://agentmods.dev/badge/skills/datacore-one/datacore-mcp/datacore-v2.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 5.1 | $0.00034 | $0.00671 |
| Opus 5 | $0.00017 | $0.00336 |
| Sonnet 5 | $0.00007 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
Datacore v2 Operating Rules 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.
What it actually says
Datacore v2 Operating Rules
Eight invariants for working in the ledger-era fleet. Each one is here because it was learned the expensive way — the rationale on every engram names the incident, not a specification.
These are operating rules, not a changelog. They answer questions an agent hits in the middle of doing something, when getting it wrong costs work.
The rules
- Merge, never rebase. Rebase renames your unpushed commits; a failed push then leaves them under an identity nobody else has seen. 50 commits lost this way on 2026-08-12.
- You own what you authored, not what you carry. After a merge, other actors' commits legitimately sit in your push range.
SKIP_PRE_PUSHis for hand-repairing a log, never for unblocking a push. A guard that fires on ordinary work teaches everyone to bypass it.- Unknown ≠ broken. Health checks report three states, not two.
- Python 3.10+. macOS
python3is 3.9 and fails at import, not runtime. - One failure must not remove unrelated capability. One bad module took away all 69 MCP tools.
- Know which checkout your job runs from. The Mac's detectors run from
~/.datacore/v2-runner, not~/Data. - Verify the artifact, and gate publishing mechanically. A source test passed while the shipped bundle still had the bug.
Why a separate pack
This is deliberately not merged into the general Datacore packs. v2 changed what is true about the system — an agent should be able to tell "this is how v2 works" from "this is Datacore generally", and this pack can be revoked cleanly at the next re-genesis without disturbing anything else.
Scope
Applies to every machine in the fleet: mac, winston, nightshift, hermes, plur-claw. If a rule here contradicts what you observe, the observation wins — report it rather than working around it. Three of these eight exist because someone reported a contradiction instead of routing around it.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 56 lines · 34 tokens per session scan A 5bae914cf04b
Datacore v2 Operating Rules is a skill published in the GitHub repository datacore-one/datacore-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 671 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 2026-08-31.
Other skills, from other repositories
agent-evaluation-reporting
Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
infisical-sync-skill
Expert knowledge for the Infisical Sync Hand — Infisical API reference, vault operations, error patterns, security guidance.
swarm-migrate
Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…
nso-device-ops
Cisco NSO device operations — config retrieval, state inspection, sync, platform info, NED IDs, device groups. Use when retrieving device configs from NSO, checking sync status, pulling platform inventory, or inspecting NSO device groups and NED drivers.
k8s-incident-triage
Read-only Kubernetes incident triage using kubectl. Accepts natural language or structured input. Produces root-cause hypotheses, evidence, and next-step commands.
Advanced Chaos Engineering
Advanced chaos engineering patterns using Chaos Monkey, Litmus, and Gremlin for testing distributed system resilience under failure conditions.