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 skills/knowhowlab/agent-testkit/test-e2enpx skills add knowhowlab/agent-testkit --skill test-e2egit clone --depth 1 https://github.com/knowhowlab/agent-testkitWhat 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 | $0.00097 | $0.01428 |
| Opus 5 | $0.00048 | $0.00714 |
| Sonnet 5 | $0.00019 | $0.00286 |
| Haiku 4.5 | $0.00010 | $0.00143 |
Grade A, and why
test-e2e 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 yesterday.
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.
(bash, file reads, edits, writes, docker operations, curl calls, How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
test-e2e — Execute the E2E plan
Goal: Run the plan in TESTS_E2E.md (repository root) from scratch:
every phase in order, every step verified against its Expect:, every
failure fixed before moving on, everything logged to
<protocol dir>/<protocol prefix>-YYYYMMDD-HHMM.md (UTC timestamp at
start; create the directory if missing).
Pre-flight
- Locate
TESTS_E2E.mdat the repo root (or nearest ancestor containing one). Missing → tell the user no plan exists and offer to runtest-initto generate it. Do not improvise a plan. - Read the whole plan. Take Meta (protocol dir/prefix), Scopes, Facts, Fixtures, Phases, Wrap-up.
- Resolve the user's arguments against
## Scopes. Unknown scope word → ask once now; after launch there is no interaction. No arguments → full plan. - Create the protocol file with its header (see format below); record the Environment commands' results; initialize counters (passed / failed / fixed / blocked / skipped).
Critical rules
- Run autonomously without user confirmation. Execute ALL commands (bash, file reads, edits, writes, docker operations, curl calls, service restarts) immediately without pausing for approval. This is an automated test suite — treat every tool call as pre-approved. Do not ask "should I continue?" — just do it.
- Fix failures immediately. When a step's result contradicts its
Expect:, do NOT skip it. Investigate the root cause, apply a fix, re-run the failing check until it passes, then continue. Check the step'sOn fail:hint and the plan's## Factsfirst — a Fact that declares the behavior expected means it is NOT a failure; never "fix" documented caveats. - Log everything, as you go. Every result (pass or fail), issue, fix, and retry goes into the protocol file the moment it happens — timestamps, exact error messages, files changed, before/after of fixes. Never batch protocol writes for the end.
- Retry timing issues once. Connection refused / service still
initializing → wait 15–30 seconds, retry once, then investigate.
Per-step
Retry:/Timeout:lines override this default. - Never skip a phase on your own. A phase that cannot pass even
after fixes is logged
BLOCKEDwith the reason, and the run continues. The only legitimate skips:SKIPPED (scope)for phases/steps excluded by the resolved scopes, andBLOCKED (prereq)forneeds-<x>tags whose prerequisite is absent on this host (record which). External-dependency steps that fail clearly upstream (per plan Facts/tags) areSKIPPED-EXTERNAL, never silent passes. - Scratch, not repo. Runtime state (configs, data dirs, logs) lives
in a fresh temp dir per run. The only repo writes allowed: the
protocol file, Fixtures the plan declares, and fixes for real
failures.
Destructive:steps must target scratch or a path the plan explicitly names. - Minimize console output. One line per phase; the protocol file is the detailed log.
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.
- yesterday First seen · 126 lines · 97 tokens per session scan A bc687af06ca6
test-e2e is a skill published in the GitHub repository knowhowlab/agent-testkit (3 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,428 once invoked, about $0.0005 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.