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/SII-Holos/synergynpx agentmods add skills/sii-holos/synergy/develop-synergyWrote 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/sii-holos/synergy/develop-synergy)<a href="https://agentmods.dev/skills/sii-holos/synergy/develop-synergy"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/develop-synergy/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/sii-holos/synergy/develop-synergy"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/develop-synergy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 17 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.
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 | $0.00064 | $0.06060 |
| Opus 5.5 | $0.00026 | $0.02424 |
| Sonnet 5.5 | $0.00013 | $0.01212 |
| Haiku 4.5 | $0.00006 | $0.00606 |
Grade A, and why
develop-synergy 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop Synergy Safely
Protect the Active Runtime
Never stop, restart, signal, or reuse the SYNERGY_HOME of the Synergy instance carrying the current task. Do not run synergy stop, broad kill/pkill, or modify its data/lock files.
For startup or migration changes, seed an isolated installed database with cold Sessions and operations before timing readiness. Run bun test test/lifecycle/history-startup.test.ts from Harness, then the affected page/recovery tests. Report Harness preparation separately from HTTP/UI readiness and actual bytes read separately from logical dataset size; never use the live Home as a performance fixture. Follow the experience measurement rules; exercise an old Session’s readable body and interactive composer after readiness, plus new Session and worktree creation under the same historical load.
Read Development reference before choosing a mode. Compare the injected synergy-runtime identity with the Session Workspace before choosing a Home, port or restart target. The host source checkout/revision describes the running backend, not necessarily the files being edited; --attach does not change backend ownership. Verify identity through an isolated model request rather than inferring it from a window title or the default port.
Check both bun --version and the executable selected by the current version manager against package.json. Invoke the pinned runtime with its directory on PATH so nested package scripts also use it; selecting an absolute parent executable alone does not pin bun commands inside those scripts. bun dev rejects incompatible parent or BUN_BIN runtimes before preparation or startup. Do not treat dependency installation as a runtime upgrade, and do not restart a shared running instance to apply a version change.
Prepare an Isolated Home
- Choose a dedicated parent directory and explicit free ports. Check listeners with
lsof -nP -iTCP -sTCP:LISTENor the platform equivalent; do not assume4097and3001are free. - Create the required
.synergyparent:
What ships with it
1 file 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.
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 · +2 lines 1a9b95fded39
- 2d ago Changed · +2 lines 19ecb979e0f5
- 4d ago Changed · +8 lines 7150274f828b
- 8d ago Changed 8ceb2db45a96
- 9d ago Changed · +2 lines 7b99642ae3e0
- 11d ago Changed · +8 lines ca09d66edbc9
- 12d ago Changed 48bfaeeb34d3
- 15d ago Changed · +4 lines 1fa54f652cdf
- 17d ago Changed · +2 lines dd7177d5680a
- 18d ago First seen · 146 lines · 64 tokens per session scan A d0cc15fe987a
develop-synergy is a skill published in the GitHub repository SII-Holos/synergy (388 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 6,060 once invoked, about $0.0003 per session on Opus 5.5. 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
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.