Borrowing it
Nothing to install: this file belongs to anantjain-xyz/symphony-rust. 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/anantjain-xyz/symphony-rust/main/.agents/skills/symphony-screenshot/SKILL.mdgit clone --depth 1 https://github.com/anantjain-xyz/symphony-rustWrote 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/anantjain-xyz/symphony-rust/symphony-screenshot)<a href="https://agentmods.dev/skills/anantjain-xyz/symphony-rust/symphony-screenshot"><img src="https://agentmods.dev/badge/skills/anantjain-xyz/symphony-rust/symphony-screenshot/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/anantjain-xyz/symphony-rust/symphony-screenshot"><img src="https://agentmods.dev/badge/skills/anantjain-xyz/symphony-rust/symphony-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.04287 |
| Opus 5.5 | $0.00021 | $0.01715 |
| Sonnet 5.5 | $0.00010 | $0.00857 |
| Haiku 4.5 | $0.00005 | $0.00429 |
Grade C, and why
symphony-screenshot scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
8. **Cleanup workspace artifacts**: `rm -rf .symphony/screenshots .symphony/capture.mjs .playwright-mcp` and `rm -f .symphony/screenshot-sha /tmp/symphony-shots.json` (those should not appear in `git status` afterward). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
6. **Verify the images render** in the PR (visual confirmation by the operator, or a `curl -I "$raw_url"` returning 200 if running unattended). Do not proceed to step 7 without confirmation — the cleanup revert removes t Copies of this mod
1 near-identical copy found in the catalogue:
- symphony-screenshot — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot
The PR description is the home for proof-of-testing screenshots. They are hosted as raw GitHub blobs at the screenshot commit SHA. After the PR body is updated, create a follow-up revert commit that removes the screenshot files from the branch tip while keeping the original screenshot commit reachable in branch history.
Capture runs through a small Node script (capture.mjs) driven from the shell, not the Playwright MCP. The MCP's browser_run_code_unsafe runs in a sandbox with no process, require, or context, so it cannot read an environment variable or inject a session cookie — authenticated dev captures are impossible there. A plain Node script gets a normal process.env, so a session cookie can be injected while the secret stays in the environment and never appears in a tool call / transcript. The script also bypasses self-signed dev certs, handles SPAs that never reach network-idle, fails on unexpected HTTP statuses, and can run interactions (hover/click/…) to reach states that aren't a bare URL.
Preconditions
- A PR exists for the current branch (use the
symphony-pushskill first if not). gh auth statussucceeds against the repo's host, and plaingit pushhas credentials for that host. If relying on GitHub CLI for HTTPS git credentials, rungh auth setup-gitfirst (gh auth setup-git --hostname <host>for a non-default host).GITHUB_TOKEN/GH_TOKENalone can authenticategh pr ...commands but is not enough for thegit push origin ...andgit push --force-with-lease ...commands this workflow runs.- Playwright is installed in the repo's
node_modules.capture.mjsdoesimport { chromium } from 'playwright', resolved from the repo tree. If the repo doesn't already depend on Playwright, install it first (npm install --no-save playwright, or the repo's package manager) —npx playwrightdoes not make the bareimportresolvable for a plainnode .symphony/capture.mjs. If it can't be installed, surface a blocker rather than guessing. - For authenticated targets only (anything behind a login wall, e.g. a dev server): the session cookie value must be present in an environment variable (do not hardcode it). You pass the env var's name and the cookie's name/domain in the spec — never the value. If the var is unset, stop and surface a blocker; do not capture the auth wall.
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.
- 2mo ago First seen · 265 lines · 52 tokens per session scan C f5279a9c3dd7
symphony-screenshot is a skill published in the GitHub repository anantjain-xyz/symphony-rust (12 stars, last pushed 16d ago), licensed MIT. It adds 52 tokens to every session and 4,287 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). 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.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.