check-session
Verify that a past Claude Code session properly ran the /bdk:audit protocol — locates the session transcript by ID and grades each audit checkpoint.
Skill by ArielIL
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/arielil-check-session
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/check-session
What's inside
- Skill name
check-session- Description
- Verify that a past Claude Code session properly ran the /bdk:audit protocol — locates the session transcript by ID and grades each audit checkpoint.
- License
- unknown
- Instructions
- 21 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from ArielIL/behavior-kit
- 0.521score
brainstorm
ArielIL
Start a behavior brainstorm session for a new feature — the mandatory first phase of BDK feature work.
SkillBFreshness: BClaude Code +9 - 0.516score
red
ArielIL
Enter or resume the RED phase — write failing behavior tests from the approved spec, with signature-only stubs in source.
SkillBFreshness: BClaude Code +9 - 0.516score
green
ArielIL
The RED→GREEN gate — verify genuine red, run the test-quality reviewer, send in the EDFH adversary, then unlock implementation.
SkillBFreshness: BClaude Code +9 - 0.516score
init
ArielIL
Set up BDK in the current project — detect the stack, write .bdk/config.json, install the doctrine rules file, and prepare gitignore entries.
SkillBFreshness: BClaude Code +9 - 0.516score
audit
ArielIL
Retro-review an existing feature against the behavior-first standard (Cooper + Wlaschin) without entering the phased workflow.
SkillBFreshness: BClaude Code +9 - 0.467score
refactor
ArielIL
Enter the REFACTOR phase — behavior-preserving structural improvement with zero new tests, protected by the green suite.
SkillCFreshness: CClaude Code +9 - 0.467score
back-to-red
ArielIL
Escape hatch — a test is wrong or the desired behavior changed; reopen RED with a logged reason so tests can be edited again.
SkillCFreshness: CClaude Code +9 - 0.467score
contract-grew
ArielIL
Escape hatch — refactoring exposed genuinely new public contract; open a new RED for that surface instead of silently testing internals.
SkillCFreshness: CClaude Code +9 - 0.467score
gear
ArielIL
Shift TDD gears for the active feature — 4 (default full cycle), 5 (skip-ahead for obvious implementations), or low (exploratory throwaway tests).
SkillCFreshness: CClaude Code +9 - 0.462score
peek
ArielIL
Escape hatch — allow Claude to read one specific source file during BRAINSTORM, logged.
SkillCFreshness: CClaude Code +9 - 0.462score
done
ArielIL
Close out the active BDK feature — final green verification, no new tests since RED, throwaway scaffolding deleted, spec finalized and archived.
SkillCFreshness: CClaude Code +9 - 0.459score
status
ArielIL
Show the current BDK feature, phase, gear, evidence freshness, and outstanding obligations.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 28, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/ArielIL/behavior-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ArielIL
- 0.521score
brainstorm
ArielIL
Start a behavior brainstorm session for a new feature — the mandatory first phase of BDK feature work.
SkillBFreshness: BClaude Code +9 - 0.516score
red
ArielIL
Enter or resume the RED phase — write failing behavior tests from the approved spec, with signature-only stubs in source.
SkillBFreshness: BClaude Code +9 - 0.516score
green
ArielIL
The RED→GREEN gate — verify genuine red, run the test-quality reviewer, send in the EDFH adversary, then unlock implementation.
SkillBFreshness: BClaude Code +9 - 0.516score
audit
ArielIL
Retro-review an existing feature against the behavior-first standard (Cooper + Wlaschin) without entering the phased workflow.
SkillBFreshness: BClaude Code +9 - 0.516score
init
ArielIL
Set up BDK in the current project — detect the stack, write .bdk/config.json, install the doctrine rules file, and prepare gitignore entries.
SkillBFreshness: BClaude Code +9 - 0.467score
back-to-red
ArielIL
Escape hatch — a test is wrong or the desired behavior changed; reopen RED with a logged reason so tests can be edited again.
SkillCFreshness: CClaude Code +9
Cite this page
check-session skill. Agent Mart. https://agentmart.dev/skills/arielil-check-session (last updated 2026-10-24)