synthesis-skills-manager

synthesis-skills-manager is a skill for Claude Code, Codex from synthesisengineering/synthesis-skills. It costs 65 tokens per session (5,969 once invoked), scanned A, original, Apache-2.0.

A manager for installing and maintaining reusable instructions for coding agents across several repositories. It tracks where skills came from and can deploy them to tools such as Codex, Claude Code, and Cursor.

In plain words
What is it for?
Use it to install or update skills, check for drift, resolve conflicting versions, record provenance, and coordinate skills across repositories and projects.
Why use it?
It helps keep personal, team, and public skills in sync and makes changes, conflicts, and outdated installations visible.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Part of the synthesis-skills plugin — 63 skills, 4 hooks shipped together

Good fit Use it to install or update skills, check for drift, resolve conflicting versions, record provenance, and coordinate skills across repositories and projects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthesisengineering/synthesis-skills/synthesis-skills-manager
Install

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.

Any agent
npx skills add synthesisengineering/synthesis-skills --skill synthesis-skills-manager
Clone the repo
git clone --depth 1 https://github.com/synthesisengineering/synthesis-skills

Made for: Claude Code, Codex.

Or install synthesis-skills, the plugin that ships this one along with the rest of its 63 skills, 4 hooks.

Wrote 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.

agentmods badge for synthesis-skills-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-skills-manager/github.svg)](https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-skills-manager)
Your own site
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-skills-manager"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-skills-manager/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.

agentmods 80×15 button for synthesis-skills-manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-skills-manager"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-skills-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,969 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

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 →

  • high Rogue Agent · line 3
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Rogue Agent · line 464
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Agent Snooping · line 103
    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.
  • medium Rogue Agent · line 226
    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 237
    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.
  • medium Agent Snooping · line 238
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.05969
Opus 5 $0.00032 $0.02985
Sonnet 5 $0.00013 $0.01194
Haiku 4.5 $0.00006 $0.00597

Measured 6d ago against content hash 5e486be1a228, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

synthesis-skills-manager 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 6d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/cache_guardian.py, scripts/release.py, scripts/test_cache_guardian.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/synthesis-skills-manager/SKILL.md · 500 lines

How it starts

The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesis Skills Manager

Version 2.7.0 (2026-09-04) deduplicates historical payloads in a SQLite content-addressed archive. Immutable per-version manifests preserve paths, types, modes and metadata; restoration creates independent files. SHA-256 validation covers every payload and manifest, beyond database structure checks. The complete database, including page overhead, stays within the unchanged 512 MiB budget. A verified candidate replaces the store atomically; legacy trees move before deletion only after their complete recovery is verified. Interrupted retirement resumes against the committed version manifest. The archive-aware standalone guardian and supervisor are verified before migration or native refresh. Source integrity includes permissions, not just bytes.

Version 2.6.3 (2026-09-03) makes synchronous historical-cache verification wait up to 120 seconds for the shared transition lock. This covers a complete budgeted historical-root restore and serializes an onboarding completion check behind an ordinary background guardian pass instead of reporting a false release collision. Watch and --once work remain nonblocking; persistent publisher contention still fails closed after the bounded wait.

Version 2.6.2 (2026-09-03) makes the publisher and the durable guardian consume one canonical integrity policy. The release snapshot and quiet-window verifier now tolerate the same narrowly bounded runtime bytecode as the guardian, so an older task can keep invoking its hook throughout a refresh without invalidating its preserved root. That boundary includes CPython's numeric-suffixed atomic-write files. A differing historical root is replaced as one directory instead of copying through untrusted entries, so a nested symlink or hard link cannot redirect repair writes outside the cache. All other source and filesystem-type checks remain fail-closed.

Version 2.6.1 (2026-09-03) bounds runtime-bytecode exclusions to real Python cache directories; unknown files, links and source changes still fail. Shipped Python hooks use -B to avoid creating bytecode there.

Version 2.6.0 (2026-09-02) includes immutable public CLI activation in the gated publication and dual-client verification transaction. The launcher binds the verified version tag, commit, Git tree and content digest.

Version 2.5.1 (2026-09-02) prioritizes the newest historical Codex roots during recovery, so the version most likely to be pinned by a just-updated task returns first instead of last. The onboarding update engine now consumes the durable guardian synchronously before reporting a successful Codex refresh and verifies the invoking task's exact hook tree. The budgeted, tag-backed archive, single-writer transition lock, supervisor, refusal of unsafe or differing content, and client-owned newest-version boundary remain unchanged.

Version 2.5.0 established the durable background guardian and kept recovery digests scoped to tracked release content rather than client-owned metadata. The whole-system onboarding suite and its scaffold/component catalog audit remain required release checks.

Manage synthesis skills across a three-repo architecture. Skills are executable methodology. Public skills are also packaged as a native plugin for clients that support plugins; private and shared skills remain native user/project skills.

Read the full file on GitHub · 500 lines

Files

What ships with it

5 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.

Changes

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.

  1. 6d ago Changed · +6 lines 5e486be1a228
  2. 7d ago Changed · +147 lines f6d3b5c075a8
  3. 11d ago First seen · 347 lines · 65 tokens per session scan A 05105273c36c

Subscribe to this mod's changes

synthesis-skills-manager is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 5,969 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens