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 instructions/synthesisengineering/synthesis-skills/agents-mdgit clone --depth 1 https://github.com/synthesisengineering/synthesis-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/synthesisengineering/synthesis-skills/agents-md)<a href="https://agentmods.dev/instructions/synthesisengineering/synthesis-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/synthesisengineering/synthesis-skills/agents-md.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 | $0.01273 | $0.01273 |
| Opus 5 | $0.00636 | $0.00636 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
synthesis-skills AGENTS.md 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 yesterday.
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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions: Synthesis Skills
Purpose
This public repository is the canonical source for portable synthesis engineering skills. It is packaged as one native plugin for OpenAI Codex and Claude Code while remaining compatible with the Agent Skills standard.
Canonical Sources
skills/owns every public skill, script, reference, asset, license, and Codex interface..codex-plugin/plugin.jsonand.claude-plugin/plugin.jsonown the two client manifests. Their versions must match..agents/plugins/marketplace.jsonand.claude-plugin/marketplace.jsonown marketplace discovery.hooks/hooks.jsonowns shared lifecycle-hook registration.install.shsupports direct-copy fallbacks and the transition to native plugins. Native plugins are the primary installation path.
Never edit installed plugin caches or user-level skill copies. Make the change
here, verify it, merge it to main, then update the installed plugins.
Implementation Rules
- Search the existing skills and scripts before adding behavior.
- Keep shared behavior agent-neutral. Put client-specific metadata and event translation in the corresponding adapter.
- Give each skill one canonical directory under
skills/. - Keep
SKILL.mdbelow 500 lines; move detailed material intoreferences/. - Keep executable behavior in version-controlled scripts with deterministic tests.
- Protective checks fail closed when required state or dependencies cannot be verified.
- Do not add compatibility shims unless the task explicitly requires them.
- Do not include credentials, private organization names, personal paths, or client-confidential examples in this public repository.
Cross-Client Contract
- Every public skill requires
SKILL.mdwith an SPDX license identifier in frontmatter andagents/openai.yaml. The repository-levelLICENSE-APACHEandLICENSE-CC0files carry the corresponding terms. - Claude Code and Codex must load the same skill source and shared scripts.
AGENTS.mdis the tracked repository instruction source.CLAUDE.mdis only the Claude Code import adapter:@AGENTS.md.- Plugin-relative paths are required; absolute paths to a local checkout are forbidden.
- Runtime conformance must verify enabled plugin state, duplicate direct copies, hooks, and project handoff behavior.
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.
- yesterday Changed · +16 lines · +246 tokens per session e78ae3c7e4a6
- 5d ago First seen · 102 lines · 1,027 tokens per session scan A 6ecefe00c3fa
synthesis-skills AGENTS.md is an instructions file published in the GitHub repository synthesisengineering/synthesis-skills (17 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,273 tokens to every session, about $0.0064 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 instructions, from other repositories
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).
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.
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 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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.