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/anantjain-xyz/symphony-rustnpx agentmods add skills/anantjain-xyz/symphony-rust/screenshotWrote 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/screenshot)<a href="https://agentmods.dev/skills/anantjain-xyz/symphony-rust/screenshot"><img src="https://agentmods.dev/badge/skills/anantjain-xyz/symphony-rust/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/screenshot"><img src="https://agentmods.dev/badge/skills/anantjain-xyz/symphony-rust/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 | $0.00026 | $0.02143 |
| Sonnet 5 | $0.00010 | $0.00857 |
| Haiku 4.5 | $0.00005 | $0.00429 |
Grade C, and why
symphony-screenshot scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
8. **Cleanup workspace artifacts**: `rm -rf .symphony/screenshots .symphony/capture.mjs .playwright-mcp` and `rm -f .symphony/screenshot-sha /tmp/symphony-shots.json` (those should not appear in `git status` afterward). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
6. **Verify the images render** in the PR (visual confirmation by the operator, or a `curl -I "$raw_url"` returning 200 if running unattended). Do not proceed to step 7 without confirmation — the cleanup revert removes t This is a copy
100% identical to symphony-screenshot — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
- 10d 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 (11 stars, last pushed 28d ago), licensed MIT. It adds 52 tokens to every session and 4,287 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). It is 100% identical to symphony-screenshot, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
desktop-screenshot
Capture desktop app screenshots and post them to GitHub PRs with immutable URLs.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.
chrome-releases
Queries Chrome commit, version, release, and milestone metadata. Use when finding the first landed Chrome version of a commit, checking channel releases across platforms, inspecting milestone schedules and branch refs, or checking version containment.
keep-sorted
Automatically detects misordered lists in code (like Android XMLs), injects go/keep-sorted tags, sorts them, and creates CLs.
cl-link-from-hash
Use this skill to get a link to a Gerrit Changelist (CL) from a given commit hash in the Chromium repository. Use when you need to find the review discussion, comments, or related issues for a specific commit. Don't use for linking to files or code lines.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.