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 skills add synthesisengineering/synthesis-skills --skill synthesis-agent-conformancegit 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/skills/synthesisengineering/synthesis-skills/synthesis-agent-conformance)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-agent-conformance"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-agent-conformance/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-agent-conformance"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-agent-conformance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 26 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 109 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00082 | $0.02717 |
| Opus 5 | $0.00041 | $0.01358 |
| Sonnet 5 | $0.00016 | $0.00543 |
| Haiku 4.5 | $0.00008 | $0.00272 |
Grade A, and why
synthesis-agent-conformance 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 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.
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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Agent Conformance
Treat cross-agent portability as a continuously tested system, not a file-count comparison.
Operating model
Verify five planes:
- Source: version-controlled skills, instructions, client adapters, hooks, project state, and configuration.
- Installed: deployed plugins and skills, generated files, catalogs, instruction budgets, runtime configuration, and Codex's authoritative hook trust state. Never infer or write trust state.
- Live: client-specific receipts created by genuine lifecycle events. A static script probe is not live evidence.
- Continuity: coordination leases, active pointers, attributed local working state, explicit remote publication, and bidirectional handoff exercises.
- Capability: authenticated read-only outcomes and explicitly supported, unsupported, or unverifiable product surfaces.
Name the plane whenever two facts appear to conflict. Runtime state determines current behavior; canonical state determines what the next deployment should produce.
Active and stopped payload parity use diagnostic context rendering: compare the complete local context, including unread messages, without acknowledging delivery, writing lifecycle receipts, checking release currency, fetching Git, fast-forwarding a checkout or refreshing a lease. Unreadable diagnostic inbox state fails closed. Validation targets the selected seat/project's inbox; demonstrably unrelated historical blocks cannot redefine its native messages or delivery keys. These probes establish agreement over local evidence, not remote freshness or actual client delivery. Other conformance checks may refresh state; do not describe the entire command as read-only.
Both client renderers and project state use the shared confined controlling-plan resolver. Structured authority precedes historical prose, parent-plan hashes invalidate stale checkpoints, and stopped comparisons remap the plan into the causally selected worktree. Missing, malformed and ambiguous legacy references remain non-green; diagnostic rendering does not rewrite history to resolve them.
What ships with it
26 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 231 B
- references/architecture.md 6.3 KB
- references/instruction-kernel-pattern.md 7.0 KB
- scripts/active_project.py 19 KB runs code
- scripts/capability_evidence.py 6.4 KB runs code
- scripts/client_binaries.py 2.8 KB runs code
- scripts/codex_app_server.py 3.4 KB runs code
- scripts/codex_hook_audit.py 5.8 KB runs code
- scripts/codex_skill_catalog.py 8.5 KB runs code
- scripts/conformance.py 94 KB runs code
- scripts/live_receipt.py 20 KB runs code
- scripts/project_context.py 3.1 KB runs code
- scripts/session_context.py 26 KB runs code
- scripts/test_active_project.py 14 KB runs code
- scripts/test_capability_evidence.py 4.0 KB runs code
- scripts/test_client_binaries.py 2.8 KB runs code
- scripts/test_codex_app_server.py 395 B runs code
- scripts/test_codex_hook_audit.py 3.5 KB runs code
- scripts/test_codex_skill_catalog.py 5.9 KB runs code
- scripts/test_conformance.py 73 KB runs code
- scripts/test_diagnostic_mode.py 4.7 KB runs code
- scripts/test_diagnostic_parity.py 18 KB runs code
- scripts/test_parity.py 6.3 KB runs code
- scripts/test_plan_reference.py 19 KB runs code
- scripts/test_session_context.py 37 KB runs code
- scripts/test_streaming_transcript.py 11 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 · +6 lines 38988bac4d61
- 4d ago Changed · +18 lines 97bba662d2b0
- 5d ago Changed 4c235bf266f5
- 6d ago Changed · +17 lines 86b9b1448fb1
- 6d ago Changed · +3 lines 0ef3423c6512
- 10d ago First seen · 223 lines · 82 tokens per session scan A 009f13b6bc11
synthesis-agent-conformance is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 2,717 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…