bf-baseline

bf-baseline is a skill for Claude Code from chan4lk/specclaw. It costs 320 tokens per session (4,744 once invoked), scanned A, original, MIT.

A harness design and recording plan for proving that a rebuilt application behaves like the older application it replaces. It covers different boundaries, such as functions, services, APIs, data, and excluded user interfaces, and checks for sources of unpredictable results.

In plain words
What is it for?
Use it to design comparison tests, generate capture code, and validate recorded fixtures for a legacy-app rebuild. It helps account for changing clocks, databases, and other non-deterministic inputs.
Why use it?
Rebuilding software can introduce small behavior changes that are hard to notice. This gives you a structured way to capture and compare expected behavior, while leaving the actual application run and capture to a human.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the specclaw plugin — 32 skills, 21 agents shipped together

Good fit Use it to design comparison tests, generate capture code, and validate recorded fixtures for a legacy-app rebuild. It helps account for changing clocks, databases, and other non-deterministic inputs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chan4lk/specclaw/bf-baseline
Install

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.

Any agent
npx skills add chan4lk/specclaw --skill bf-baseline
Clone the repo
git clone --depth 1 https://github.com/chan4lk/specclaw

Made for: Claude Code.

Or install specclaw, the plugin that ships this one along with the rest of its 32 skills, 21 agents.

Wrote 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.

agentmods badge for bf-baseline

README.md
[![agentmods](https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-baseline/github.svg)](https://agentmods.dev/skills/chan4lk/specclaw/bf-baseline)
Your own site
<a href="https://agentmods.dev/skills/chan4lk/specclaw/bf-baseline"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-baseline/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.

agentmods 80×15 button for bf-baseline

Your own site · 80×15
<a href="https://agentmods.dev/skills/chan4lk/specclaw/bf-baseline"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/bf-baseline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 320 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,744 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00320 $0.04744
Opus 5 $0.00160 $0.02372
Sonnet 5 $0.00064 $0.00949
Haiku 4.5 $0.00032 $0.00474

Measured 3d ago against content hash dbb08f2c0e39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bf-baseline 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 3d 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.

plugins/specclaw/skills/bf-baseline/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

specclaw bf-baseline

First, run specclaw-ensure-init .specclaw — idempotently creates .specclaw/ if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name).

Design, generate, and record the golden-master harness for proving behavioral equivalence between the legacy app and its rebuild. Read-only side-command — no specclaw-validate-change call, no <change> involved, matching the analyze/architecture/domain/rebuild-plan/clarify pattern.

This command does not run the legacy app and does not capture fixtures itself, in any mode. Designing the harness (Mode A), generating the runnable capture code (Mode B, --harness), and validating a capture (Mode C, --record) are all separate from actually running a capture — that step is always a human, running the generated harness's own build/test command (whatever the identified stack's conventional one is) themselves. That boundary is deliberate: capture needs a real build, possibly a real database, and human judgment about which scenarios matter.

Mode A — design (default: no flag)

If the user's message contains --module MOD-###, this is a module-scoped design — read the sub-section at the end of this mode before doing anything, because steps 2 and 4 change.

  1. Collect:

    specclaw-bf-baseline collect .specclaw [--module MOD-###]
    

    Requires .specclaw/analysis/domain-model.md to exist — scenarios are derived from its numbered business rules. If it exits non-zero, surface its stderr message to the user verbatim and stop — it names /specclaw:bf-domain as the command to run first. Don't retry, don't design scenarios from nothing. Also reports which supplementary documents (codebase-report.md, architecture.md, functional-spec.md, rebuild-backlog.md) are present, for the agent's own stack detection and backlog-item linkage.

    It additionally reports the module map (soft input — its PROPOSED/CONFIRMED status plus every module's owned DR-### rules, so each scenario can declare the module(s) owning the rules it pins) and the prior scenario roster with the next free GM-### id. --module makes the map a hard requirement and fails if the id names no active module.

Read the full file on GitHub · 141 lines

Changes

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.

  1. 3d ago First seen · 141 lines · 320 tokens per session scan A dbb08f2c0e39

Subscribe to this mod's changes

bf-baseline is a skill published in the GitHub repository chan4lk/specclaw (12 stars, last pushed 4d ago), licensed MIT. It adds 320 tokens to every session and 4,744 once invoked, about $0.0016 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.

Related

Other skills, from other repositories

run-preflight

A release pre-check workflow that builds the mini-app, runs automated checks, explains errors, and lists review items that require a person to test the app on a real device. A preflight check is a final inspection before submission.

TOKTOKHAN-DEV/agent-company · 3 tokens

ai-dev-team

The AI Dev Team contract — how work is run in any project using this framework: proportional process, TDD, behaviour-only tickets, which process skills exist and when to reach for them, and the git conventions. Load this at the START of any development task, when picking an agent or handing off between roles, and…

olehsvyrydov/AI-development-team · 84 tokens

product-verification

Drive the running product and verify it works end-to-end. Use this skill after a deploy, before a release, or when the user says "verify", "smoke test", "does it work", "test the flow", "check staging", "end-to-end test", or "drive the product". Also use when the user wants to verify a specific user journey (signup…

rbah31/claude-code-workflow · 112 tokens

smoke-test

Post-sprint validation. Verifies the application works as expected after a sprint completes. Use after any sprint or deployment, or when the user says "smoke test", "verify it works", "test the app", "does it still work", "regression check", "post-deploy check", or "sanity check". Invoked by SP-QA during post-sprint…

rbah31/claude-code-workflow · 83 tokens

implement

Use in the Implement phase whenever writing or editing production Java code, or fixing a bug, in a Spring/Spring Boot project. Enforces test-first (red-green-refactor), executes the approved plan step by step, and honors the project's path-scoped tech-stack rules and the task's enforcement set. Preloaded into…

taipt1504/claudehut · 73 tokens

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens