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 robertsfeir/atelier-pipeline --skill brain-uninstallgit clone --depth 1 https://github.com/robertsfeir/atelier-pipelineWrote 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/robertsfeir/atelier-pipeline/brain-uninstall)<a href="https://agentmods.dev/skills/robertsfeir/atelier-pipeline/brain-uninstall"><img src="https://agentmods.dev/badge/skills/robertsfeir/atelier-pipeline/brain-uninstall/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.
<a href="https://agentmods.dev/skills/robertsfeir/atelier-pipeline/brain-uninstall"><img src="https://agentmods.dev/badge/skills/robertsfeir/atelier-pipeline/brain-uninstall.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00053 | $0.03141 |
| Opus 5 | $0.00026 | $0.01571 |
| Sonnet 5 | $0.00011 | $0.00628 |
| Haiku 4.5 | $0.00005 | $0.00314 |
Grade A, and why
brain-uninstall 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain Plugin -- Uninstall
This skill guides the user through removing or disconnecting the brain plugin's persistent memory layer. Per ADR-0055, the brain ships as a standalone mybrain plugin (separate from atelier-pipeline). This skill targets the brain config and database — it does NOT uninstall the mybrain plugin itself (use claude plugin uninstall mybrain for that). Run this conversationally -- ask questions one at a time, not as a list. Present what will be removed BEFORE doing anything destructive.
Detection: Locate Config
Before asking anything, find the brain config file:
- Check if
.claude/brain-config.jsonexists in the project root (shared config). - Check if
${CLAUDE_PLUGIN_DATA}/brain-config.jsonexists (personal config). - If both exist, note both. The shared config is the project-level config; the personal config is the user's local override.
- If neither exists, stop:
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.
- 11d ago First seen · 363 lines · 53 tokens per session scan A 6f25e3f8ecd1
brain-uninstall is a skill published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,141 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
lembas
Use between workflow phases or when context feels bloated. Writes a structured checkpoint capturing task, findings, files, state, and next steps, then continues from that summary instead of the full history. Invoke standalone or automatically between quest phases.
session-handoff-number-collision-with-unmerged-sibling
Detect and recover from a session-number collision when running session-handoff and a parallel/sibling session has authored a same-numbered handoff doc that hasn't merged into main yet. Use when: (1) you're in session-handoff Phase 1 about to write docs/handoffs/sessionNNNhandoff.md, (2) ls docs/handoffs/ shows the…
wrap
Use when ending a session, wrapping up, or saying "session end", "wrap up", "update files". Reviews the conversation and updates brain files, workflows, registry, and decisions log based on what happened.
claude-code-projects-jsonl-worktree-fanout
Find a prior session's transcript that /.claude/projects/ / does not hold: each git worktree gets its own separately namespaced project directory.
continuous-learning
ProductionOS instinct-based learning system. Observes sessions via hooks, extracts patterns, creates atomic instincts with confidence scoring, and auto-promotes high-confidence patterns across projects.
context-driven-development
Use this skill when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md, and workflow.md files.