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 bdfinst/agentic-dev-team/plugin install dev-teamWrote 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/bdfinst/agentic-dev-team/harness-e2e-check)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/harness-e2e-check"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/harness-e2e-check/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/bdfinst/agentic-dev-team/harness-e2e-check"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/harness-e2e-check.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 | $0.00137 | $0.01947 |
| Opus 5.5 | $0.00055 | $0.00779 |
| Sonnet 5.5 | $0.00027 | $0.00389 |
| Haiku 4.5 | $0.00014 | $0.00195 |
Grade A, and why
harness-e2e-check 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 1mo 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness E2E Check
Role: worker. This command drives real, live exercises of the harness's own
mechanisms in throwaway scratch fixtures and reports pass/fail with evidence
— it does not modify the plugin, and it is not a substitute for /agent-eval
(per-agent detection accuracy) or /harness-audit (usage-metrics-driven
staleness analysis). It exists because those mechanisms only prove
themselves working together, in a live run, not from each one's own
isolated unit tests.
Worker constraints
- Read-only against the plugin itself. All exercises run inside scratch
directories (a fresh
mktemp -dper item, or the caller's--outputsibling) — never inside the plugin's own working tree. - Live, not simulated. Where a mechanism can be exercised without an
LLM call (guard hooks,
lesson_validate.py, structural gates, stale-reference scans), run the real script/hook against a real fixture — never hand-wave "this should work." Where a mechanism genuinely requires a live/buildrun (Steps 3-4 below), drive it for real via/headless-runor an equivalent live session — do not substitute a description of what a run would show. - Be concise. Report each item as one line (pass/fail + one-line evidence pointer), then a short summary. Full transcripts/output go to the scratch dir, not chat.
- Every run maintains
references/watchlist.md. See "Hardening over time" below — this is not optional bookkeeping, it's the point of running this repeatedly instead of once.
Parse Arguments
Arguments: $ARGUMENTS
- No argument: run all 8 items below.
--item N: run only item N (1-6).--output <path>: write the full report to a specific path. Default:.dev-team-reports/harness-e2e-check-<date>.md.
The 8 items
Each item mirrors one from issue #907's original test plan. Item numbers are stable — do not renumber even if an item is skipped or split.
Item 1 — Full automated suite
Run the repo's actual CI-equivalent gate (scripts/ci-local.sh, or the
component pytest suites directly: plugins/dev-team/tests, tests/repo,
tests/agents, tests/commands, tests/scripts, tests/hooks). Zero
regressions is the bar — a red suite is a fail for this item, full stop.
What ships with it
3 files 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.
- 1mo ago First seen · 162 lines · 137 tokens per session scan A 7e603034d524
harness-e2e-check is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 137 tokens to every session and 1,947 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
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.
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…
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.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.