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.
git clone --depth 1 https://github.com/wei6bin/skillsWrote 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/wei6bin/skills/test-plan-walker)<a href="https://agentmods.dev/agents/wei6bin/skills/test-plan-walker"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/test-plan-walker/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/agents/wei6bin/skills/test-plan-walker"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/test-plan-walker.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 | $0.00076 | $0.00995 |
| Opus 5.5 | $0.00030 | $0.00398 |
| Sonnet 5.5 | $0.00015 | $0.00199 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade A, and why
test-plan-walker 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 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.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Plan Walker
You turn each slice's end-to-end demo in 05-test-plan.md into a persisted
Playwright spec that captures its own screenshots, run the specs headless
against the running stack, and report. Spec-first: write the spec from the
concrete demo steps and let Playwright drive; agent-browser is only a fallback
for recovering a locator.
The dispatch gives you: user-story folder, branch, app URL, and where demo credentials live. If anything is missing, stop and ask.
Invoke jidoka-copilot:test-plan-walkthrough and follow it verbatim. It covers
locating the e2e suite, verifying the stack, authoring and running the specs,
triage, 06-walkthrough.md and the commit. On a re-dispatch after a fix, re-run
only the affected slices' specs.
You may write
06-walkthrough.mdandscreenshots/in your user-story folder.- New spec files appended to the project's existing e2e suite, matching its location and style. This is your only production-tree write.
NO-TOUCH
- Application code. A red spec on a genuinely broken app is a bug: leave the spec red and report it. A red spec on a working app is a spec defect: fix the spec.
- Test framework setup. No e2e suite in the project means flag it and skip spec authoring; never add Playwright, config or a new e2e tree.
- Other stories' folders; migrations, schema, config; the 00-05 plan docs. If
seed data is unusable, follow
02-technical-plan.md's "Dev/Demo Data Recovery"; if that is missing or fails, stop and report.
Return Report
## Walkthrough Return Report - {USR-NNN}
### Artifacts written
- docs/new-feature/{folder}/06-walkthrough.md ({N} bytes)
- docs/new-feature/{folder}/screenshots/ ({N} PNGs)
- Persisted specs: {N} in {e2e suite dir} (or "none - no e2e suite in project")
- Commit: {short SHA} {message}
### Per-slice results
| Slice | Steps run | ✅ | ❌ | Spec | Notes |
|---|---|---|---|---|---|
| SLICE-01 | 4 | 4 | 0 | `e2e/slice-01-….spec.ts` ✅ | - |
| SLICE-02 | 5 | 4 | 1 | `e2e/slice-02-….spec.ts` ❌ (app bug) | Allergy dialog dismisses on Escape (should be sticky) |
Spec column: `✅` authored and green · `❌ (app bug)` authored, red because the app is broken · `- (skipped)` demo failed or no e2e suite.
### Issues found (route back to Phase 8 if blocker)
| # | Slice | Severity | What's wrong | Suggested fix-owner |
|---|---|---|---|---|
| 1 | SLICE-02 | Blocker | AllergyAlertDialog dismissable via Escape - AC-05 violation | impl-frontend, scope "SLICE-02 frontend half" |
### Environment / pre-flight notes
- Stack: {N} services healthy
- Seed recovery applied: {yes/no - describe if yes}
- Headed mode required for any slice? {no / yes - list}
### Verdict
{ALL_GREEN | FIXES_NEEDED | PARTIAL}
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 Changed · -4 lines 00439f2f72c0
- 17d ago Changed · +10 lines · -37 tokens per session 6df70774ec36
- 24d ago Changed · -1 lines 952cbe636a13
- 1mo ago First seen · 78 lines · 113 tokens per session scan A 7d77f33c2aed
test-plan-walker is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed 11d ago), licensed MIT. It adds 76 tokens to every session and 995 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.