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-promotion-gateWrote 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-promotion-gate)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-promotion-gate"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-promotion-gate/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-promotion-gate"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-promotion-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.02038 |
| Opus 5 | $0.00043 | $0.01019 |
| Sonnet 5 | $0.00017 | $0.00408 |
| Haiku 4.5 | $0.00009 | $0.00204 |
Grade A, and why
synthesis-promotion-gate 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 11d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Promotion Gate
Doctrine
A successful build is not a publication-safety signal. A build establishes that a renderer accepted its inputs. Promotion requires a second judgment over the outgoing artifacts, in the representations the destination exposes.
This skill supplies that boundary for configured promotion scaffolding. It does not decide whether ordinary prose is appropriate to disclose, prove that an undeclared consumer does not exist, or grant publication or deployment permission. Those approval gates remain in force. A clean receipt is evidence only for the exact policy, inputs, renderers, routes, representations, and command recorded in it.
Two Commands, Two Authority Classes
check builds and inspects but cannot change publication state:
python3 skills/synthesis-promotion-gate/scripts/promotion_gate.py check \
--config .agents/promotion-gate.yaml \
--receipt .agents/receipts/promotion-check.json
Its receipt is an acceptance-test, with authority_receipt: false.
enforce is the production entry point. It builds into an isolated temporary root,
captures each expected output exactly once, inspects those captured bytes, closes the
output universe, materializes a separate content snapshot, writes a candidate receipt,
and re-hashes the contract and snapshot immediately before the boundary. It then
invokes the supplied promotion command. The command must carry both
{candidate_receipt} and {output_root} as literal arguments; the gate substitutes
the exact receipt and captured-snapshot paths.
python3 skills/synthesis-promotion-gate/scripts/promotion_gate.py enforce \
--config .agents/promotion-gate.yaml \
--receipt .agents/receipts/promotion-enforced.json \
-- python3 tools/promote.py {candidate_receipt} {output_root}
Only a clean enforce run whose supplied command returns zero issues an
enforced-gate receipt with authority_receipt: true. A dirty artifact, missing route,
changed input, changed policy, failed build, or failed promotion command refuses the
transition. The receipt withholds matched content and records a digest instead.
What ships with it
10 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.
- acceptance-suite.yaml 7.3 KB
- agents/openai.yaml 301 B
- fixtures/destination-representations.yaml 3.6 KB
- scripts/promotion_gate.py 57 KB runs code
- scripts/test_promotion_gate.py 31 KB runs code
- scripts/test_skill_contract.py 3.9 KB runs code
- templates/acceptance-suite.example.yaml 695 B
- templates/marker-policy.example.yaml 1.6 KB
- templates/promotion-gate.example.yaml 1.3 KB
- templates/surface-manifest.example.yaml 264 B
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.
- 11d ago First seen · 188 lines · 85 tokens per session scan A 5192533f1dc7
synthesis-promotion-gate is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 2,038 once invoked, about $0.0004 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 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…