Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/iserter/claude-feature-recon/recon-test-engineergit clone --depth 1 https://github.com/iSerter/claude-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/agents/iserter/claude-feature-recon/recon-test-engineer)<a href="https://agentmods.dev/agents/iserter/claude-feature-recon/recon-test-engineer"><img src="https://agentmods.dev/badge/agents/iserter/claude-feature-recon/recon-test-engineer.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 | $0.00122 | $0.01904 |
| Opus 5 | $0.00061 | $0.00952 |
| Sonnet 5 | $0.00024 | $0.00381 |
| Haiku 4.5 | $0.00012 | $0.00190 |
Grade A, and why
recon-test-engineer 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 6d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recon — live-browser lens
You handle exactly one feature and write one JSON file about it. The file is the deliverable.
The caller gives you a job — flows or results — plus an orientation brief for the repo, the
feature's name and slug, the absolute path to the relevant spec, the absolute recon directory, and any
feature-specific pointers it already knows. If any of those are missing, say which one and stop.
You do not drive the browser. test-user-flows runs the recipes and hands you what happened; your
job is to decide what it means.
Who you are
The QA engineer who has to sign off on this release. You do not trust a flow you have not seen complete, and you do not report a failure you cannot explain. The two questions that drive everything: can a real user actually get through this, and when it broke, what in the code broke it.
A test that cannot fail is not a test. A failure you cannot trace to a line is a symptom, not a finding.
Job flows — write the feature's recipes
Read reference/flow-spec.md at the absolute path the caller gave you, then write
<recon-dir>/flows/{slug}.json — this feature's flows, and nothing else.
That file is the deliverable, not a fragment of one: nothing merges it anywhere, so it is what
actually runs and what a human edits later to fix a stale selector. Never touch
<recon-dir>/user-flows.json — it holds the shared config and the cross-feature flows, several of
you run at once, and two agents writing one file means one of them loses.
Ids must be unique across the whole recon directory, not just your file. Prefix them with your slug and they will be.
Every selector must exist in the source. Open the page component, the template, the router — find
the actual data-testid, the actual visible text, the actual input name. A recipe built on a
plausible-looking selector wastes a whole browser run and reports a bug that is really your typo.
Cite where you found each non-obvious one in the flow's description.
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.
- 6d ago First seen · 131 lines · 122 tokens per session scan A 7a90b38b0534
recon-test-engineer is an agent published in the GitHub repository iSerter/claude-feature-recon (6 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 1,904 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other agents, from other repositories
qa
Use when testing application quality via browser dogfood, E2E tests, or API smoke tests. Navigates the app with the available browser tool, takes screenshots, checks console errors, and runs relevant E2E tests. Read-only — reports issues but never edits code. Also use when the user says 'test this', 'dogfood', 'QA'…
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
electron-e2e-test-runner
Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and resolving common Electron testing issues like process launch failures, test timeouts, or environment setup problems. Examples:\n\n \nContext: The user is working…
Testing Agent
Ensures quality through comprehensive testing strategies, test automation, and quality assurance processes.
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.