Borrowing it
Nothing to install: this file belongs to equinor/fusion-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/equinor/fusion-skills/main/.github/instructions/skills-greenkeeping.instructions.mdgit clone --depth 1 https://github.com/equinor/fusion-skillsWrote 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/instructions/equinor/fusion-skills/skills-greenkeeping)<a href="https://agentmods.dev/instructions/equinor/fusion-skills/skills-greenkeeping"><img src="https://agentmods.dev/badge/instructions/equinor/fusion-skills/skills-greenkeeping/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/instructions/equinor/fusion-skills/skills-greenkeeping"><img src="https://agentmods.dev/badge/instructions/equinor/fusion-skills/skills-greenkeeping.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 | $0.01328 | $0.01328 |
| Opus 5 | $0.00664 | $0.00664 |
| Sonnet 5 | $0.00266 | $0.00266 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade C, and why
fusion-skills skills-greenkeeping.instructions.md scanned grade C with 2 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 12d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
2. Block remote-script execution patterns (for example `curl ... | sh` or equivalent). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. Block remote-script execution patterns (for example `curl ... | sh` or equivalent). How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills greenkeeping instructions
Apply when maintaining skills in skills/**.
Goal
Keep skill catalog discoverable, current, high-quality, secure, owned.
Greenkeeping activities and triggers
Run greenkeeping when at least one of the following happens:
- A PR changes
skills/**content (SKILL.md,assets/**,references/**,scripts/**). - A new skill is added or an existing skill is moved, deprecated, or removed.
- MCP server requirements or compatibility expectations change.
- A scheduled maintenance sweep is due (recommended cadence: at least monthly).
- A reliability or security incident identifies stale/unsafe skill guidance.
For each greenkeeping run, cover all activity lanes:
| # | Lane | Focus |
|---|---|---|
| 1 | Discovery audit | Activation cues, tags, findability |
| 2 | Currency audit | Metadata, dependencies, compatibility |
| 3 | Quality audit | Structure, completeness, references |
| 4 | Security audit | Unsafe patterns, secret exposure risk |
| 5 | Ownership and lifecycle audit | Owner/sponsor, status, deprecation path |
| 6 | Workflow-policy alignment audit | Governance handoff, policy drift |
Metadata standards and currency checks
Required frontmatter:
namedescriptionmetadata.version
Required ownership metadata:
metadata.owner(required): primary accountable maintainer.- Use a stable GitHub identity (
@useror@org/team). - Avoid personal names without GitHub identity.
- Use a stable GitHub identity (
metadata.sponsor(optional): backup accountability owner (team or maintainer).metadata.deprecated_at(required for skills inskills/.deprecated/): date the skill was deprecated inYYYY-MM-DDformat. Validated by CI.
Discovery and currency checks:
descriptionclearly states what the skill does and when to use it.metadata.tagsremains present and relevant to current scope.metadata.mcp.requiredandmetadata.mcp.suggestedmatch actual tool needs.metadata.role,metadata.orchestrator, andmetadata.skillsremain internally consistent.compatibilitytext (if present) reflects current prerequisites.- Existing skill
metadata.versionis not manually bumped in regular PRs; use changesets and release automation flow.
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.
- 12d ago First seen · 149 lines · 1,328 tokens per session scan C 580d348a67b1
fusion-skills skills-greenkeeping.instructions.md is an instructions file published in the GitHub repository equinor/fusion-skills (1 stars, last pushed 3d ago), licensed MIT. It adds 1,328 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).