Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/synthesisengineering/synthesis-skillsnpx agentmods add skills/synthesisengineering/synthesis-skills/synthesis-onboardingWrote 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/synthesisengineering/synthesis-skills/synthesis-onboarding)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-onboarding"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-onboarding/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/synthesisengineering/synthesis-skills/synthesis-onboarding"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-onboarding.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 | $0.00106 | $0.03861 |
| Opus 5 | $0.00053 | $0.01930 |
| Sonnet 5 | $0.00021 | $0.00772 |
| Haiku 4.5 | $0.00011 | $0.00386 |
Grade C, and why
synthesis-onboarding 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 2d 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.
curl -fsSL https://raw.githubusercontent.com/synthesisengineering/synthesis-skills/stable/onboard.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/synthesisengineering/synthesis-skills/stable/onboard.sh | sh How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Onboarding
One bootstrap and one stable synthesis command manage the public synthesis
work system. The engine is convergent and transactional: it records desired
state separately from machine observations, stages each mutation, commits only
after its probes pass, and preserves an aborted receipt when work fails.
Start here
Full system, the default:
curl -fsSL https://raw.githubusercontent.com/synthesisengineering/synthesis-skills/stable/onboard.sh | sh
Skills only, through the same bootstrap:
curl -fsSL https://raw.githubusercontent.com/synthesisengineering/synthesis-skills/stable/onboard.sh | sh -s -- setup --profile skills-only
After bootstrap, use the installed public command:
synthesis setup [--profile full|skills-only] [--clients claude,codex]
[--channel stable|edge] [--pin X.Y.Z]
[--answers PATH] [--org-repo URL | --invite PATH]
[--personal-instruction-source PATH]
[--adopt-workspace-instructions]
[--clear-personal-instruction-source]
synthesis enroll --org-repo URL | --invite PATH
[--personal-instruction-source PATH]
[--adopt-workspace-instructions]
[--clear-personal-instruction-source]
synthesis update
synthesis repair
synthesis status [--json]
synthesis doctor [--json]
synthesis workspace ensure --name NAME [--remote URL]
synthesis outcome verify --task TASK --workspace PATH --source-class CLASS
synthesis uninstall [--purge]
synthesis status and synthesis doctor print a plain summary by default:
profile, policy, release, generation, each truth plane, and one next action.
--json returns the structured payload instead.
synthesis update and synthesis repair migrate an older plugin-only receipt
automatically when it contains no workspace, organization, or generated-resource
state. Richer or unreadable legacy state is never guessed; run synthesis setup
to select the intended profile explicitly. An update that finds each client
already at the selected release on the selected marketplace ref reports
"no refresh needed" and leaves the client installations untouched; only a
version change or a policy transition reconfigures a marketplace.
What ships with it
46 files 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.
- agents/openai.yaml 283 B
- references/components.json 2.5 KB
- references/instruction-sources.schema.json 1.4 KB
- references/invite.schema.json 985 B
- references/kernel.example.md 1.3 KB
- references/layers.json 2.8 KB
- references/machine-observation.schema.json 1.9 KB
- references/org-manifest.md 9.8 KB
- references/personal-policy.example.json 622 B
- references/release-capabilities.json 3.9 KB
- references/release-descriptor.schema.json 1.4 KB
- references/scaffolds.json 1.1 KB
- references/system-state.schema.json 7.0 KB
- scripts/bootstrap.py 10 KB runs code
- scripts/check_capabilities.py 7.7 KB runs code
- scripts/check_scaffolds.py 5.4 KB runs code
- scripts/direct_copy.sh 24 KB runs code
- scripts/enrollment.py 17 KB runs code
- scripts/kernel_sync.py 4.7 KB runs code
- scripts/onboard.py 195 KB runs code
- scripts/organization.py 7.0 KB runs code
- scripts/plugin_currency.py 13 KB runs code
- scripts/reload_guidance.py 1.5 KB runs code
- scripts/runtime_payload.py 29 KB runs code
- scripts/synthesis_cli.py 68 KB runs code
- scripts/system_contract.py 106 KB runs code
- scripts/test_additive_enrollment.py 45 KB runs code
- scripts/test_bootstrap.py 11 KB runs code
- scripts/test_check_capabilities.py 1.3 KB runs code
- scripts/test_independent_review.py 44 KB runs code
- scripts/test_instruction_adversarial.py 31 KB runs code
- scripts/test_instruction_convergence.py 6.5 KB runs code
- scripts/test_kb_adversarial.py 16 KB runs code
- scripts/test_kb_update_ownership.py 14 KB runs code
- scripts/test_long_transcript.py 15 KB runs code
- scripts/test_onboard.py 65 KB runs code
- scripts/test_organization.py 5.3 KB runs code
- scripts/test_plugin_currency.py 7.2 KB runs code
- scripts/test_reload_guidance.py 20 KB runs code
- scripts/test_runtime_doctors.py 7.5 KB runs code
- scripts/test_runtime_integration.py 27 KB runs code
- scripts/test_runtime_payload.py 35 KB runs code
- scripts/test_synthesis_cli.py 47 KB runs code
- scripts/test_system_contract.py 40 KB runs code
- scripts/test_updater_doctor.py 12 KB runs code
- scripts/whole_system.py 17 KB runs code
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.
- 2d ago Changed · +23 lines f3b1967b81e6
- 4d ago Changed · +30 lines bed19b452d9c
- 5d ago Changed · +80 lines b42598873928
- 6d ago Changed · +31 lines 18e90f0a2372
- 7d ago Changed · +37 lines · -2 tokens per session a887be961372
- 10d ago First seen · 166 lines · 108 tokens per session scan C 41a3c91972ee
synthesis-onboarding is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 106 tokens to every session and 3,861 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…