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/chan4lk/specclaw/bf-e2enpx skills add chan4lk/specclaw --skill bf-e2egit clone --depth 1 https://github.com/chan4lk/specclawWrote 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/chan4lk/specclaw/bf-e2e)<a href="https://agentmods.dev/skills/chan4lk/specclaw/bf-e2e"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-e2e.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 | $0.00146 | $0.00833 |
| Opus 5 | $0.00073 | $0.00417 |
| Sonnet 5 | $0.00029 | $0.00167 |
| Haiku 4.5 | $0.00015 | $0.00083 |
Grade A, and why
bf-e2e 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 today.
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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specclaw bf-e2e
First, run specclaw-ensure-init .specclaw — idempotently creates .specclaw/ if it doesn't exist (silent if already initialized).
Generate E2E test coverage for a target application, driven by a universal E2E automation architect agent. Read-only side-command — no specclaw-validate-change call, no <change> involved, matching the analyze/bf-architecture/bf-baseline pattern.
-
Resolve the target path. If the user's message names a path, use it (validate it exists and is inside the repo). Otherwise default to the repository root.
-
Check for golden-master fixtures:
ls .specclaw/baseline/fixtures/GM-*.json 2>/dev/nullThis is a soft input, not a hard requirement — if empty, proceed anyway (the agent generates tests from the described flow instead and flags the gap; see its Task 4). If present, resolve the full list of fixture filenames to pass along.
-
Check for prior context (soft — pass paths if present, don't fail if absent):
[ -f .specclaw/analysis/codebase-report.md ] && echo present [ -f .specclaw/baseline/scenarios.md ] && echo present -
Spawn the automation agent:
Agenttool,subagent_type: "bf-e2e-architect", on the model fromconfig.yamlmodels.coding(default:anthropic/claude-sonnet-5) — this agent writes real, runnable test code, the same routing as build's coding agents, not the read-only analysis agents. Pass as context:- The resolved target path.
- The resolved
.specclaw/baseline/fixtures/path and the list ofGM-*.jsonfilenames found in Step 2 (empty list is valid input). - The resolved paths of
codebase-report.mdandscenarios.md, if present (Step 3). - Any flow/feature description the user included in their invocation of this skill.
-
The agent detects platform/stack, selects the E2E framework, and writes the page object(s) and test script(s) itself, per its own Output section — this skill does not write any file itself.
-
Relay the agent's full response to the user as-is — it already carries the required Detection Summary → Setup/Execution Commands → Page Object File(s) → SpecClaw Test Script structure. Do not summarize it away; the human needs the actual generated code and commands, not a paraphrase.
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.
- today First seen · 38 lines · 146 tokens per session scan A ad22c5245387
bf-e2e is a skill published in the GitHub repository chan4lk/specclaw (12 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 833 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
local-llm-expert
Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio. Expert in quantization formats (GGUF, EXL2) and local AI privacy.
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
agent-neural-network
Agent skill for neural-network - invoke with $agent-neural-network.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
neural-training
Neural pattern training with SONA (Self-Optimizing Neural Architecture), MoE (Mixture of Experts), and EWC++ for knowledge consolidation. Use when: pattern learning, model optimization, knowledge transfer, adaptive routing. Skip when: simple tasks, no learning required, one-off operations.