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 skills add jessepinkman9900/claude-second-brain --skill pack-testgit clone --depth 1 https://github.com/jessepinkman9900/claude-second-brainWrote 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/jessepinkman9900/claude-second-brain/pack-test)<a href="https://agentmods.dev/skills/jessepinkman9900/claude-second-brain/pack-test"><img src="https://agentmods.dev/badge/skills/jessepinkman9900/claude-second-brain/pack-test.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 5.1 | $0.00087 | $0.04186 |
| Opus 5 | $0.00044 | $0.02093 |
| Sonnet 5 | $0.00017 | $0.00837 |
| Haiku 4.5 | $0.00009 | $0.00419 |
Grade D, and why
pack-test scanned grade D with 2 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 8d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls $VAULT_A/wiki/ $VAULT_A/raw-sources/ $VAULT_A/.claude/skills/ $VAULT_A/scripts/qmd/ Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.claude-second-brain/test-brain-a How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pack Test
Tests the npm package as it behaves when published. Uses npx to run from the local tarball — pnpm dlx doesn't support local tarball paths (it tries to resolve them as scoped package names). After publishing, pnpm dlx claude-second-brain from the registry works fine.
Multi-brain architecture: brains live at ~/.claude-second-brain/<name>/ and are registered in ~/.claude-second-brain/config.toml. Global skills (~/.claude/skills/brain-*) are plain SKILL.md files with a sibling .csb-version sidecar. They resolve paths at call time via the claude-second-brain path and claude-second-brain qmd subcommands — no paths are baked into the skills themselves.
Important: This test mutates ~/.claude-second-brain/ and ~/.claude/skills/brain-*. If the user has real brains registered, warn them before running — cleanup removes config.toml and the test brains, which does NOT delete their real brain folders but DOES remove their registry entries and overwrite their global skills.
Steps
Run each step in order. Stop and report if any step fails.
Step 1 — Pre-flight: back up existing state
# If the user has existing brains, these are affected:
ls -la ~/.claude-second-brain/ 2>/dev/null || echo "(no existing brains)"
cat ~/.claude-second-brain/config.toml 2>/dev/null || echo "(no existing config)"
If config.toml exists with real brains, back it up so the test cleanup doesn't lose them:
cp ~/.claude-second-brain/config.toml ~/.claude-second-brain/config.toml.bak 2>/dev/null || true
Step 2 — Pack
npm pack
Produces claude-second-brain-<version>.tgz in the repo root. Verify the tarball appears before continuing.
Step 3 — Scaffold first brain
npx -y claude-second-brain-$(node -p "require('./package.json').version").tgz test-brain-a
Pass test-brain-a as the brain name argument to skip the interactive prompt. Non-TTY stdin skips the GitHub prompt. The brain is created at ~/.claude-second-brain/test-brain-a/.
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.
- 8d ago First seen · 248 lines · 87 tokens per session scan D b47f6d64f5b0
pack-test is a skill published in the GitHub repository jessepinkman9900/claude-second-brain (47 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 4,186 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
AI Release Guardian
Analyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, run configurable quality gates, and produce a go/no-go release report with cited evidence. Recommends only; never merges or deploys.
release-verification
A release-verification checklist for software versions and packages. It covers changelogs, tests, packaging, installation smoke checks, version-control actions, publishing, and checks after release.
orchestrate-release-engineer
Run the final release gate: fresh-clone simulation, artifact freshness, packaging hygiene, documentation accuracy. Use in the final hour. Catches the defects that make a working submission fail on someone else's machine.
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.