Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add iSerter/claude-feature-recon/plugin install feature-reconWrote 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/iserter/claude-feature-recon/test-user-flows)<a href="https://agentmods.dev/skills/iserter/claude-feature-recon/test-user-flows"><img src="https://agentmods.dev/badge/skills/iserter/claude-feature-recon/test-user-flows.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.01992 |
| Opus 5 | $0.00044 | $0.00996 |
| Sonnet 5 | $0.00018 | $0.00398 |
| Haiku 4.5 | $0.00009 | $0.00199 |
Grade A, and why
test-user-flows scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w '%{http_code}' <baseUrl from user-flows.json> How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test User Flows
Runs the recipes in <recon-dir>/user-flows.json (shared config + cross-feature flows) and
<recon-dir>/flows/*.json (one file per feature) against the live app, and writes two things:
<recon-dir>/e2e-test-results.json— what happened. Step-by-step status, console errors, failed requests, screenshots.<recon-dir>/features/{slug}.e2e.json— what it means. Report-spec findings withpath:lineevidence, merged into the dashboard as thee2elens.
Those are deliberately separate. A timeout is not a bug report until someone has traced it to a line of code, and that trace is the valuable part.
This is the only part of feature-recon that leaves static analysis. A finding here was reproduced, not inferred — which makes it the strongest evidence in the report, and also the only lens that can retire a finding the sweep got wrong.
Bundled files live beside this SKILL.md (${CLAUDE_PLUGIN_ROOT}/skills/test-user-flows/):
run_flows.mjs. The flow spec is at
${CLAUDE_PLUGIN_ROOT}/skills/identify-user-flows/reference/flow-spec.md, the report spec at
${CLAUDE_PLUGIN_ROOT}/skills/feature-recon/reference/report-spec.md, and the agent at
${CLAUDE_PLUGIN_ROOT}/agents/recon-test-engineer.md. Always pass absolute paths.
Requires Node 20+ and Playwright — unlike the core sweep, which runs on either python3 or node.
sh ${CLAUDE_PLUGIN_ROOT}/scripts/install-deps.sh reports what is missing.
Procedure
1. Resolve arguments
<recon-dir>— defaultdocs/recon, or--dir <path>.--feature <slug>/--only <flowId>— run a subset. Results for flows you did not run are kept.--headed— watch it happen. Worth it the first time, and when a failure makes no sense.--retries 1— retry a failed flow once, to separate a real defect from a race.--no-findings— run and record only; skip the agent pass.
If there are no recipes, stop and tell the user to run /identify-user-flows first. Do not invent
recipes here — this skill runs them, it does not write them.
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.
- 7d ago First seen · 149 lines · 89 tokens per session scan A b31edff54493
test-user-flows is a skill published in the GitHub repository iSerter/claude-feature-recon (6 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,992 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.