Synara is a local-first desktop workspace for coding agents that brings projects, agent sessions, files, execution tools, and review features into one application. It is intended for people who use coding agents to organize tasks and inspect their work.
Borrowing it
Nothing to install: this file belongs to Emanuele-web04/synara. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Emanuele-web04/synara/main/.claude/skills/verify/SKILL.mdgit clone --depth 1 https://github.com/Emanuele-web04/synaraWrote 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/emanuele-web04/synara/verify)<a href="https://agentmods.dev/skills/emanuele-web04/synara/verify"><img src="https://agentmods.dev/badge/skills/emanuele-web04/synara/verify/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/emanuele-web04/synara/verify"><img src="https://agentmods.dev/badge/skills/emanuele-web04/synara/verify.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 | $0.00017 | $0.01881 |
| Opus 5.5 | $0.00007 | $0.00752 |
| Sonnet 5.5 | $0.00003 | $0.00376 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
verify 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 28d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify: run Synara locally for runtime verification
How to launch an isolated Synara instance (server + web) to observe UI changes, without touching ~/.synara or the default dev ports.
Launch
# 1. Server (from the directory you want as the workspace/project cwd):
SYNARA_HOME=<scratch>/synara-home \
SYNARA_PORT=3899 SYNARA_MODE=web SYNARA_NO_BROWSER=1 \
VITE_DEV_SERVER_URL=http://localhost:5899 \
bun <repo>/apps/server/src/index.ts &
# 2. Web (vite dev):
cd <repo>/apps/web && PORT=5899 VITE_WS_URL=ws://localhost:3899 bun run dev &
Then open http://localhost:5899/.
Gotchas
- Preflight the ports before launching: run
lsof -nP -iTCP:<port> -sTCP:LISTENon both the server and web ports (check IPv4 and IPv6 listeners — a:::portentry collides even when127.0.0.1looks free). If you usescripts/dev-runner.ts dev, read its dry-run output for the real port map first. SYNARA_AUTH_TOKENis inherited from the launching shell: a server started with it set requires auth the web client does not have, which produces a healthy-but-disconnected UI. Unset it in the isolated test process only — never strip it from production policy.VITE_DEV_SERVER_URLon the server is required — without it the WS handshake from the vite origin is rejected with 403 (seeapps/server/src/trustedOrigins.ts).VITE_WS_URLon the web side tells the app where the WS server lives (apps/web/src/wsTransport.ts).- Default ports are 3773 (server) / 5733 (web), with no automatic per-checkout offset. The dev runner uses an explicit
SYNARA_PORT_OFFSETor derives an offset fromSYNARA_DEV_INSTANCEwhen supplied — pick explicit distinct ports and confirm the dry-run output to avoid colliding with a running dev instance. - Add a disposable git workspace through the sidebar's Projects → Add project button and enter its absolute folder path. If New project in the composer picker does not open the dialog, use this sidebar entry point instead.
- To see diffs: select a git workspace with uncommitted changes, then click the +N −N toggle in the top-right chat header — it opens the DiffPanel (working-tree diff). No project/thread needed.
- Server tests: don't run the suite from a checkout under
/private/tmp—localImageRoute.test.tsfails there (its "outside the workspace" fixture lands in an allowed temp root). It passes from a normal checkout and on CI.
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.
- 28d ago Changed · +41 lines 1fcfe3c85c6c
- 1mo ago Changed · +47 lines · +17 tokens per session 882c5476ee5f
- 2mo ago First seen · 32 lines · 0 tokens per session scan A 43a2cf2e8d6f
verify is a skill published in the GitHub repository Emanuele-web04/synara (2,152 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,881 once invoked, about $0.0001 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
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…
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.
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.